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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.30 by root, Thu Oct 23 02:46:20 2008 UTC vs.
Revision 1.66 by root, Fri Dec 31 06:18:30 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 ();	46	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	47	use AnyEvent::Util ();
48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
50		49
51	use base Exporter::;	50	use base Exporter::;
52		51
53	our $VERSION = '1.05';	52	our $VERSION = '1.5';
54		53
55	our @EXPORT = qw(http_get http_post http_head http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
56		55
57	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	56	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
61	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
62		61
63	# changing these is evil	62	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
65	our $MAX_PER_HOST = 4;	64	our $MAX_PER_HOST = 4;
66		65
67	our $PROXY;	66	our $PROXY;
68	our $ACTIVE = 0;	67	our $ACTIVE = 0;
69		68
…		…
92	must be an absolute http or https URL.	91	must be an absolute http or https URL.
93		92
94	When called in void context, nothing is returned. In other contexts,	93	When called in void context, nothing is returned. In other contexts,
95	C<http_request> returns a "cancellation guard" - you have to keep the	94	C<http_request> returns a "cancellation guard" - you have to keep the
96	object at least alive until the callback get called. If the object gets	95	object at least alive until the callback get called. If the object gets
97	destroyed before the callbakc is called, the request will be cancelled.	96	destroyed before the callback is called, the request will be cancelled.
98		97
99	The callback will be called with the response data as first argument	98	The callback will be called with the response body data as first argument
100	(or C<undef> if it wasn't available due to errors), and a hash-ref with	99	(or C<undef> if an error occured), and a hash-ref with response headers as
101	response headers as second argument.	100	second argument.
102		101
103	All the headers in that hash are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
105	contain the three parts of the HTTP Status-Line of the same name. The	105	three parts of the HTTP Status-Line of the same name. If an error occurs
		106	during the body phase of a request, then the original C<Status> and
		107	C<Reason> values from the header are available as C<OrigStatus> and
		108	C<OrigReason>.
		109
106	pseudo-header C<URL> contains the original URL (which can differ from the	110	The pseudo-header C<URL> contains the actual URL (which can differ from
107	requested URL when following redirects).	111	the requested URL when following redirects - for example, you might get
		112	an error that your URL scheme is not supported even though your URL is a
		113	valid http URL because it redirected to an ftp URL, in which case you can
		114	look at the URL pseudo header).
108		115
		116	The pseudo-header C<Redirect> only exists when the request was a result
		117	of an internal redirect. In that case it is an array reference with
		118	the C<($data, $headers)> from the redirect response. Note that this
		119	response could in turn be the result of a redirect itself, and C<<
		120	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
		122
109	If the server sends a header multiple lines, then their contents will be	123	If the server sends a header multiple times, then their contents will be
110	joined together with C<\x00>.	124	joined together with a comma (C<,>), as per the HTTP spec.
111		125
112	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	127	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
114	and the C<Reason> pseudo-header will contain an error message.	128	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		129	message.
115		130
116	A typical callback might look like this:	131	A typical callback might look like this:
117		132
118	sub {	133	sub {
119	my ($body, $hdr) = @_;	134	my ($body, $hdr) = @_;
…		…
137		152
138	=item headers => hashref	153	=item headers => hashref
139		154
140	The request headers to use. Currently, C<http_request> may provide its	155	The request headers to use. Currently, C<http_request> may provide its
141	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	156	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
142	and will provide defaults for C<User-Agent:> and C<Referer:>.	157	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		158	suppressed by using C<undef> for these headers in which case they won't be
		159	sent at all).
143		160
144	=item timeout => $seconds	161	=item timeout => $seconds
145		162
146	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
147	the timeout, as will read or write activity. Default timeout is 5 minutes.	164	the timeout, as will read or write activity, i.e. this is not an overall
		165	timeout.
		166
		167	Default timeout is 5 minutes.
148		168
149	=item proxy => [$host, $port[, $scheme]] or undef	169	=item proxy => [$host, $port[, $scheme]] or undef
150		170
151	Use the given http proxy for all requests. If not specified, then the	171	Use the given http proxy for all requests. If not specified, then the
152	default proxy (as specified by C<$ENV{http_proxy}>) is used.	172	default proxy (as specified by C<$ENV{http_proxy}>) is used.
153		173
154	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	174	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
155	HTTPS.	175	HTTPS.
156		176
157	=item body => $string	177	=item body => $string
158		178
159	The request body, usually empty. Will be-sent as-is (future versions of	179	The request body, usually empty. Will be-sent as-is (future versions of
…		…
165	based on the original netscape specification.	185	based on the original netscape specification.
166		186
167	The C<$hash_ref> must be an (initially empty) hash reference which will	187	The C<$hash_ref> must be an (initially empty) hash reference which will
168	get updated automatically. It is possible to save the cookie_jar to	188	get updated automatically. It is possible to save the cookie_jar to
169	persistent storage with something like JSON or Storable, but this is not	189	persistent storage with something like JSON or Storable, but this is not
170	recommended, as expire times are currently being ignored.	190	recommended, as expiry times are currently being ignored.
171		191
172	Note that this cookie implementation is not of very high quality, nor	192	Note that this cookie implementation is not of very high quality, nor
173	meant to be complete. If you want complete cookie management you have to	193	meant to be complete. If you want complete cookie management you have to
174	do that on your own. C<cookie_jar> is meant as a quick fix to get some	194	do that on your own. C<cookie_jar> is meant as a quick fix to get some
175	cookie-using sites working. Cookies are a privacy disaster, do not use	195	cookie-using sites working. Cookies are a privacy disaster, do not use
176	them unless required to.	196	them unless required to.
		197
		198	=item tls_ctx => $scheme \| $tls_ctx
		199
		200	Specifies the AnyEvent::TLS context to be used for https connections. This
		201	parameter follows the same rules as the C<tls_ctx> parameter to
		202	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		203	C<high> can be specified, which give you a predefined low-security (no
		204	verification, highest compatibility) and high-security (CA and common-name
		205	verification) TLS context.
		206
		207	The default for this option is C<low>, which could be interpreted as "give
		208	me the page, no matter what".
		209
		210	=item on_prepare => $callback->($fh)
		211
		212	In rare cases you need to "tune" the socket before it is used to
		213	connect (for exmaple, to bind it on a given IP address). This parameter
		214	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		215	and behaves exactly the same way (e.g. it has to provide a
		216	timeout). See the description for the C<$prepare_cb> argument of
		217	C<AnyEvent::Socket::tcp_connect> for details.
		218
		219	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		220
		221	In even rarer cases you want total control over how AnyEvent::HTTP
		222	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		223	to do this, but you can provide your own C<tcp_connect> function -
		224	obviously, it has to follow the same calling conventions, except that it
		225	may always return a connection guard object.
		226
		227	There are probably lots of weird uses for this function, starting from
		228	tracing the hosts C<http_request> actually tries to connect, to (inexact
		229	but fast) host => IP address caching or even socks protocol support.
		230
		231	=item on_header => $callback->($headers)
		232
		233	When specified, this callback will be called with the header hash as soon
		234	as headers have been successfully received from the remote server (not on
		235	locally-generated errors).
		236
		237	It has to return either true (in which case AnyEvent::HTTP will continue),
		238	or false, in which case AnyEvent::HTTP will cancel the download (and call
		239	the finish callback with an error code of C<598>).
		240
		241	This callback is useful, among other things, to quickly reject unwanted
		242	content, which, if it is supposed to be rare, can be faster than first
		243	doing a C<HEAD> request.
		244
		245	Example: cancel the request unless the content-type is "text/html".
		246
		247	on_header => sub {
		248	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		249	},
		250
		251	=item on_body => $callback->($partial_body, $headers)
		252
		253	When specified, all body data will be passed to this callback instead of
		254	to the completion callback. The completion callback will get the empty
		255	string instead of the body data.
		256
		257	It has to return either true (in which case AnyEvent::HTTP will continue),
		258	or false, in which case AnyEvent::HTTP will cancel the download (and call
		259	the completion callback with an error code of C<598>).
		260
		261	This callback is useful when the data is too large to be held in memory
		262	(so the callback writes it to a file) or when only some information should
		263	be extracted, or when the body should be processed incrementally.
		264
		265	It is usually preferred over doing your own body handling via
		266	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		267	only used to create a connection, C<want_body_handle> is the better
		268	alternative, as it allows you to install your own event handler, reducing
		269	resource usage.
		270
		271	=item want_body_handle => $enable
		272
		273	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		274	changes considerably: after parsing the headers, and instead of
		275	downloading the body (if any), the completion callback will be
		276	called. Instead of the C<$body> argument containing the body data, the
		277	callback will receive the L<AnyEvent::Handle> object associated with the
		278	connection. In error cases, C<undef> will be passed. When there is no body
		279	(e.g. status C<304>), the empty string will be passed.
		280
		281	The handle object might or might not be in TLS mode, might be connected to
		282	a proxy, be a persistent connection etc., and configured in unspecified
		283	ways. The user is responsible for this handle (it will not be used by this
		284	module anymore).
		285
		286	This is useful with some push-type services, where, after the initial
		287	headers, an interactive protocol is used (typical example would be the
		288	push-style twitter API which starts a JSON/XML stream).
		289
		290	If you think you need this, first have a look at C<on_body>, to see if
		291	that doesn't solve your problem in a better way.
177		292
178	=back	293	=back
179		294
180	Example: make a simple HTTP GET request for http://www.nethype.de/	295	Example: make a simple HTTP GET request for http://www.nethype.de/
181		296
…		…
237	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	352	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
238		353
239	_slot_schedule $_[0];	354	_slot_schedule $_[0];
240	}	355	}
241		356
		357	# continue to parse $_ for headers and place them into the arg
		358	sub parse_hdr() {
		359	my %hdr;
		360
		361	# things seen, not parsed:
		362	# p3pP="NON CUR OTPi OUR NOR UNI"
		363
		364	$hdr{lc $1} .= ",$2"
		365	while /\G
		366	([^:\000-\037]*):
		367	[\011\040]*
		368	((?: [^\012]+ \| \012[\011\040] )*)
		369	\012
		370	/gxc;
		371
		372	/\G$/
		373	or return;
		374
		375	# remove the "," prefix we added to all headers above
		376	substr $_, 0, 1, ""
		377	for values %hdr;
		378
		379	\%hdr
		380	}
		381
		382	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		383
		384	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		385	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		386
242	sub http_request($$@) {	387	sub http_request($$@) {
243	my $cb = pop;	388	my $cb = pop;
244	my ($method, $url, %arg) = @_;	389	my ($method, $url, %arg) = @_;
245		390
246	my %hdr;	391	my %hdr;
		392
		393	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		394	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
247		395
248	$method = uc $method;	396	$method = uc $method;
249		397
250	if (my $hdr = $arg{headers}) {	398	if (my $hdr = $arg{headers}) {
251	while (my ($k, $v) = each %$hdr) {	399	while (my ($k, $v) = each %$hdr) {
252	$hdr{lc $k} = $v;	400	$hdr{lc $k} = $v;
253	}	401	}
254	}	402	}
255		403
		404	# pseudo headers for all subsequent responses
		405	my @pseudo = (URL => $url);
		406	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		407
256	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	408	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
257		409
258	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	410	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
259	if $recurse < 0;	411	if $recurse < 0;
260		412
261	my $proxy = $arg{proxy} \|\| $PROXY;	413	my $proxy = $arg{proxy} \|\| $PROXY;
262	my $timeout = $arg{timeout} \|\| $TIMEOUT;	414	my $timeout = $arg{timeout} \|\| $TIMEOUT;
263		415
264	$hdr{"user-agent"} \|\|= $USERAGENT;
265
266	my ($scheme, $authority, $upath, $query, $fragment) =	416	my ($uscheme, $uauthority, $upath, $query, $fragment) =
267	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	417	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
268		418
269	$scheme = lc $scheme;	419	$uscheme = lc $uscheme;
270		420
271	my $uport = $scheme eq "http" ? 80	421	my $uport = $uscheme eq "http" ? 80
272	: $scheme eq "https" ? 443	422	: $uscheme eq "https" ? 443
273	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	423	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
274		424
275	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
276
277	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	425	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
278	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	426	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
279		427
280	my $uhost = $1;	428	my $uhost = $1;
281	$uport = $2 if defined $2;	429	$uport = $2 if defined $2;
282		430
		431	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		432	unless exists $hdr{host};
		433
283	$uhost =~ s/^\[(.*)\]$/$1/;	434	$uhost =~ s/^\[(.*)\]$/$1/;
284	$upath .= "?$query" if length $query;	435	$upath .= $query if length $query;
285		436
286	$upath =~ s%^/?%/%;	437	$upath =~ s%^/?%/%;
287		438
288	# cookie processing	439	# cookie processing
289	if (my $jar = $arg{cookie_jar}) {	440	if (my $jar = $arg{cookie_jar}) {
290	%$jar = () if $jar->{version} < 1;	441	%$jar = () if $jar->{version} != 1;
291		442
292	my @cookie;	443	my @cookie;
293		444
294	while (my ($chost, $v) = each %$jar) {	445	while (my ($chost, $v) = each %$jar) {
295	if ($chost =~ /^\./) {	446	if ($chost =~ /^\./) {
…		…
302		453
303	while (my ($cpath, $v) = each %$v) {	454	while (my ($cpath, $v) = each %$v) {
304	next unless $cpath eq substr $upath, 0, length $cpath;	455	next unless $cpath eq substr $upath, 0, length $cpath;
305		456
306	while (my ($k, $v) = each %$v) {	457	while (my ($k, $v) = each %$v) {
307	next if $scheme ne "https" && exists $v->{secure};	458	next if $uscheme ne "https" && exists $v->{secure};
		459	my $value = $v->{value};
		460	$value =~ s/([\\"])/\\$1/g;
308	push @cookie, "$k=$v->{value}";	461	push @cookie, "$k=\"$value\"";
309	}	462	}
310	}	463	}
311	}	464	}
312		465
313	$hdr{cookie} = join "; ", @cookie	466	$hdr{cookie} = join "; ", @cookie
314	if @cookie;	467	if @cookie;
315	}	468	}
316		469
317	my ($rhost, $rport, $rpath); # request host, port, path	470	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
318		471
319	if ($proxy) {	472	if ($proxy) {
320	($rhost, $rport, $scheme) = @$proxy;	473	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
321	$rpath = $url;	474
		475	$rscheme = "http" unless defined $rscheme;
		476
		477	# don't support https requests over https-proxy transport,
		478	# can't be done with tls as spec'ed, unless you double-encrypt.
		479	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
322	} else {	480	} else {
323	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	481	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
324	$hdr{host} = $uhost;
325	}	482	}
326		483
		484	# leave out fragment and query string, just a heuristic
		485	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		486	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
		487
327	$hdr{"content-length"} = length $arg{body};	488	$hdr{"content-length"} = length $arg{body}
		489	if length $arg{body} \|\| $method ne "GET";
		490
		491	$hdr{connection} = "close TE";
		492	$hdr{te} = "trailers" unless exists $hdr{te};
328		493
329	my %state = (connect_guard => 1);	494	my %state = (connect_guard => 1);
330		495
331	_get_slot $uhost, sub {	496	_get_slot $uhost, sub {
332	$state{slot_guard} = shift;	497	$state{slot_guard} = shift;
333		498
334	return unless $state{connect_guard};	499	return unless $state{connect_guard};
335		500
336	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	501	my $connect_cb = sub {
337	$state{fh} = shift	502	$state{fh} = shift
		503	or do {
		504	my $err = "$!";
		505	%state = ();
338	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	506	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
		507	};
339		508
340	delete $state{connect_guard}; # reduce memory usage, save a tree	509	pop; # free memory, save a tree
		510
		511	return unless delete $state{connect_guard};
341		512
342	# get handle	513	# get handle
343	$state{handle} = new AnyEvent::Handle	514	$state{handle} = new AnyEvent::Handle
344	fh => $state{fh},	515	fh => $state{fh},
345	($scheme eq "https" ? (tls => "connect") : ());	516	peername => $rhost,
		517	tls_ctx => $arg{tls_ctx},
		518	# these need to be reconfigured on keepalive handles
		519	timeout => $timeout,
		520	on_error => sub {
		521	%state = ();
		522	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		523	},
		524	on_eof => sub {
		525	%state = ();
		526	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		527	},
		528	;
346		529
347	# limit the number of persistent connections	530	# limit the number of persistent connections
		531	# keepalive not yet supported
348	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	532	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
349	++$KA_COUNT{$_[1]};	533	# ++$KA_COUNT{$_[1]};
350	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	534	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		535	# --$KA_COUNT{$_[1]}
		536	# };
351	$hdr{connection} = "keep-alive";	537	# $hdr{connection} = "keep-alive";
352	delete $hdr{connection}; # keep-alive not yet supported
353	} else {	538	# } else {
354	delete $hdr{connection};	539	# delete $hdr{connection};
355	}	540	# }
356		541
357	# (re-)configure handle	542	$state{handle}->starttls ("connect") if $rscheme eq "https";
358	$state{handle}->timeout ($timeout);
359	$state{handle}->on_error (sub {
360	my $errno = "$!";
361	%state = ();
362	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
363	});
364	$state{handle}->on_eof (sub {
365	%state = ();
366	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
367	});
368		543
		544	# handle actual, non-tunneled, request
		545	my $handle_actual_request = sub {
		546	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		547
369	# send request	548	# send request
370	$state{handle}->push_write (	549	$state{handle}->push_write (
371	"$method $rpath HTTP/1.0\015\012"	550	"$method $rpath HTTP/1.1\015\012"
372	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	551	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
373	. "\015\012"	552	. "\015\012"
374	. (delete $arg{body})	553	. (delete $arg{body})
375	);
376
377	%hdr = (); # reduce memory usage, save a kitten
378
379	# status line
380	$state{handle}->push_read (line => qr/\015?\012/, sub {
381	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
382	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
383
384	my %hdr = ( # response headers
385	HTTPVersion => "\x00$1",
386	Status => "\x00$2",
387	Reason => "\x00$3",
388	URL => "\x00$url"
389	);	554	);
390		555
391	# headers, could be optimized a bit	556	# return if error occured during push_write()
		557	return unless %state;
		558
		559	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		560
		561	# status line and headers
392	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	562	$state{handle}->push_read (line => $qr_nlnl, sub {
		563	my $keepalive = pop;
		564
393	for ("$_[1]\012") {	565	for ("$_[1]") {
394	# we support spaces in field names, as lotus domino	566	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
395	# creates them (actually spaces around seperators
396	# are strictly allowed in http, they are a security issue).
397	$hdr{lc $1} .= "\x00$2"
398	while /\G
399	([^:\000-\037]+):
400	[\011\040]*
401	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
402	\015?\012
403	/gxc;
404		567
		568	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
		569	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
		570
		571	push @pseudo,
		572	HTTPVersion => $1,
		573	Status => $2,
		574	Reason => $3,
405	/\G$/	575	;
		576
		577	my $hdr = parse_hdr
406	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	578	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		579
		580	%hdr = (%$hdr, @pseudo);
407	}	581	}
408		582
409	substr $_, 0, 1, ""	583	# redirect handling
410	for values %hdr;	584	# microsoft and other shitheads don't give a shit for following standards,
		585	# try to support some common forms of broken Location headers.
		586	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		587	$hdr{location} =~ s/^\.\/+//;
411		588
412	my $finish = sub {	589	my $url = "$rscheme://$uhost:$uport";
413	# TODO: use destroy method, when/if available	590
		591	unless ($hdr{location} =~ s/^\///) {
		592	$url .= $upath;
		593	$url =~ s/\/[^\/]*$//;
		594	}
		595
		596	$hdr{location} = "$url/$hdr{location}";
		597	}
		598
		599	my $redirect;
		600
		601	if ($recurse) {
		602	my $status = $hdr{Status};
		603
		604	# industry standard is to redirect POST as GET for
		605	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		606	# also, the UA should ask the user for 301 and 307 and POST,
		607	# industry standard seems to be to simply follow.
		608	# we go with the industry standard.
		609	if ($status == 301 or $status == 302 or $status == 303) {
		610	# HTTP/1.1 is unclear on how to mutate the method
		611	$method = "GET" unless $method eq "HEAD";
		612	$redirect = 1;
		613	} elsif ($status == 307) {
		614	$redirect = 1;
		615	}
		616	}
		617
		618	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
414	#$state{handle}->destroy;	619	$state{handle}->destroy if $state{handle};
415	$state{handle}->on_eof (undef);
416	$state{handle}->on_error (undef);
417	%state = ();	620	%state = ();
418		621
		622	if (defined $_[1]) {
		623	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		624	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		625	}
		626
419	# set-cookie processing	627	# set-cookie processing
420	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {	628	if ($arg{cookie_jar}) {
421	for (split /\x00/, $hdr{"set-cookie"}) {	629	for ($hdr{"set-cookie"}) {
422	my ($cookie, @arg) = split /;\s*/;	630	# parse NAME=VALUE
423	my ($name, $value) = split /=/, $cookie, 2;	631	my @kv;
424	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);	632
425		633	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		634	my $name = $1;
		635	my $value = $3;
		636
		637	unless ($value) {
		638	$value = $2;
		639	$value =~ s/\\(.)/$1/gs;
		640	}
		641
		642	push @kv, $name => $value;
		643
		644	last unless /\G\s*;/gc;
		645	}
		646
		647	last unless @kv;
		648
		649	my $name = shift @kv;
		650	my %kv = (value => shift @kv, @kv);
		651
426	my $cdom;	652	my $cdom;
427	my $cpath = (delete $kv{path}) \|\| "/";	653	my $cpath = (delete $kv{path}) \|\| "/";
428		654
429	if (exists $kv{domain}) {	655	if (exists $kv{domain}) {
430	$cdom = delete $kv{domain};	656	$cdom = delete $kv{domain};
431		657
432	$cdom =~ s/^\.?/./; # make sure it starts with a "."	658	$cdom =~ s/^\.?/./; # make sure it starts with a "."
…		…
441	}	667	}
442		668
443	# store it	669	# store it
444	$arg{cookie_jar}{version} = 1;	670	$arg{cookie_jar}{version} = 1;
445	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	671	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		672
		673	redo if /\G\s*,/gc;
446	}	674	}
447	}	675	}
448		676
449	# microsoft and other shitheads don't give a shit for following standards,	677	if ($redirect && exists $hdr{location}) {
450	# try to support some common forms of broken Location headers.	678	# we ignore any errors, as it is very common to receive
451	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {	679	# Content-Length != 0 but no actual body
452	$_[1]{location} =~ s/^\.\/+//;	680	# we also access %hdr, as $_[1] might be an erro
453		681	http_request (
454	my $url = "$scheme://$uhost:$uport";	682	$method => $hdr{location},
455
456	unless ($_[1]{location} =~ s/^\///) {
457	$url .= $upath;
458	$url =~ s/\/[^\/]*$//;
459	}	683	%arg,
460		684	recurse => $recurse - 1,
461	$_[1]{location} = "$url/$_[1]{location}";	685	Redirect => [$_[0], \%hdr],
462	}	686	$cb);
463
464	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
465	# apparently, mozilla et al. just change POST to GET here
466	# more research is needed before we do the same
467	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
468	} elsif ($_[1]{Status} == 303 && $recurse) {
469	# even http/1.1 is unclear on how to mutate the method
470	$method = "GET" unless $method eq "HEAD";
471	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
472	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {
473	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
474	} else {	687	} else {
475	$cb->($_[0], $_[1]);	688	$cb->($_[0], \%hdr);
476	}	689	}
477	};	690	};
478		691
479	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	692	my $len = $hdr{"content-length"};
		693
		694	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		695	$finish->(undef, 598 => "Request cancelled by on_header");
		696	} elsif (
		697	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		698	or $method eq "HEAD"
		699	or (defined $len && !$len)
		700	) {
		701	# no body
480	$finish->(undef, \%hdr);	702	$finish->("", undef, undef, 1);
481	} else {	703	} else {
482	if (exists $hdr{"content-length"}) {	704	# body handling, many different code paths
483	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	705	# - no body expected
484	# could cache persistent connection now	706	# - want_body_handle
485	if ($hdr{connection} =~ /\bkeep-alive\b/i) {	707	# - te chunked
486	# but we don't, due to misdesigns, this is annoyingly complex	708	# - 2x length known (with or without on_body)
		709	# - 2x length not known (with or without on_body)
		710	if (!$redirect && $arg{want_body_handle}) {
		711	$_[0]->on_eof (undef);
		712	$_[0]->on_error (undef);
		713	$_[0]->on_read (undef);
		714
		715	$finish->(delete $state{handle});
		716
		717	} elsif ($hdr{"transfer-encoding"} =~ /chunked/) {
		718	my $body = undef;
		719	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		720
		721	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		722
		723	my $read_chunk; $read_chunk = sub {
		724	warn $_[1];#d#
		725	$_[1] =~ /^([0-9a-fA-F]+)/
		726	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		727
		728	my $len = hex $1;
		729
		730	if ($len) {
		731	$_[0]->push_read (chunk => hex $1, sub {
		732	$on_body->($_[1], \%hdr)
		733	or return $finish->(undef, 598 => "Request cancelled by on_body");
		734
		735	$_[0]->push_read (line => sub {
		736	length $_[1]
		737	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
		738	$_[0]->push_read (line => $read_chunk);
		739	});
		740	});
		741	} else {
		742	$_[0]->push_read (line => $qr_nlnl, sub {
		743	if (length $_[1]) {
		744	for ("$_[1]") {
		745	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		746
		747	my $hdr = parse_hdr
		748	or return $finish->(undef, 599 => "Garbled response trailers");
		749
		750	%hdr = (%hdr, %$hdr);
		751	}
		752	}
		753
		754	$finish->($body, undef, undef, 1);
		755	});
		756	}
		757	};
		758
		759	$_[0]->push_read (line => $read_chunk);
		760
		761	} elsif ($arg{on_body}) {
		762	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		763
		764	if ($len) {
		765	$_[0]->on_read (sub {
		766	$len -= length $_[0]{rbuf};
		767
		768	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		769	or return $finish->(undef, 598 => "Request cancelled by on_body");
		770
		771	$len > 0
		772	or $finish->("", undef, undef, 1);
487	};	773	});
488		774	} else {
		775	$_[0]->on_eof (sub {
489	$finish->($_[1], \%hdr);	776	$finish->("");
		777	});
		778	$_[0]->on_read (sub {
		779	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		780	or $finish->(undef, 598 => "Request cancelled by on_body");
		781	});
490	});	782	}
491	} else {	783	} else {
492	# too bad, need to read until we get an error or EOF,
493	# no way to detect winged data.
494	$_[0]->on_error (sub {
495	$finish->($_[0]{rbuf}, \%hdr);
496	});
497	$_[0]->on_eof (undef);	784	$_[0]->on_eof (undef);
		785
		786	if ($len) {
		787	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		788	$_[0]->on_read (sub {
		789	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
		790	if $len <= length $_[0]{rbuf};
		791	});
		792	} else {
		793	$_[0]->on_error (sub {
		794	($! == Errno::EPIPE \|\| !$!)
		795	? $finish->(delete $_[0]{rbuf})
		796	: $finish->(undef, 599 => $_[2]);
		797	});
498	$_[0]->on_read (sub { });	798	$_[0]->on_read (sub { });
		799	}
499	}	800	}
500	}	801	}
501	});	802	});
502	});	803	};
503	}, sub {	804
504	$timeout	805	# now handle proxy-CONNECT method
		806	if ($proxy && $uscheme eq "https") {
		807	# oh dear, we have to wrap it into a connect request
		808
		809	# maybe re-use $uauthority with patched port?
		810	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		811	$state{handle}->push_read (line => $qr_nlnl, sub {
		812	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		813	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
		814
		815	if ($2 == 200) {
		816	$rpath = $upath;
		817	&$handle_actual_request;
		818	} else {
		819	%state = ();
		820	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
		821	}
		822	});
		823	} else {
		824	&$handle_actual_request;
		825	}
505	};	826	};
		827
		828	my $tcp_connect = $arg{tcp_connect}
		829	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		830
		831	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		832
506	};	833	};
507		834
508	defined wantarray && AnyEvent::Util::guard { %state = () }	835	defined wantarray && AnyEvent::Util::guard { %state = () }
509	}	836	}
510		837
…		…
524	&http_request	851	&http_request
525	}	852	}
526		853
527	=back	854	=back
528		855
		856	=head2 DNS CACHING
		857
		858	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		859	the actual connection, which in turn uses AnyEvent::DNS to resolve
		860	hostnames. The latter is a simple stub resolver and does no caching
		861	on its own. If you want DNS caching, you currently have to provide
		862	your own default resolver (by storing a suitable resolver object in
		863	C<$AnyEvent::DNS::RESOLVER>).
		864
529	=head2 GLOBAL FUNCTIONS AND VARIABLES	865	=head2 GLOBAL FUNCTIONS AND VARIABLES
530		866
531	=over 4	867	=over 4
532		868
533	=item AnyEvent::HTTP::set_proxy "proxy-url"	869	=item AnyEvent::HTTP::set_proxy "proxy-url"
534		870
535	Sets the default proxy server to use. The proxy-url must begin with a	871	Sets the default proxy server to use. The proxy-url must begin with a
536	string of the form C<http://host:port> (optionally C<https:...>).	872	string of the form C<http://host:port> (optionally C<https:...>), croaks
		873	otherwise.
		874
		875	To clear an already-set proxy, use C<undef>.
		876
		877	=item $date = AnyEvent::HTTP::format_date $timestamp
		878
		879	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		880	Date (RFC 2616).
		881
		882	=item $timestamp = AnyEvent::HTTP::parse_date $date
		883
		884	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX
		885	timestamp, or C<undef> if the date cannot be parsed.
537		886
538	=item $AnyEvent::HTTP::MAX_RECURSE	887	=item $AnyEvent::HTTP::MAX_RECURSE
539		888
540	The default value for the C<recurse> request parameter (default: C<10>).	889	The default value for the C<recurse> request parameter (default: C<10>).
541		890
542	=item $AnyEvent::HTTP::USERAGENT	891	=item $AnyEvent::HTTP::USERAGENT
543		892
544	The default value for the C<User-Agent> header (the default is	893	The default value for the C<User-Agent> header (the default is
545	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	894	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
546		895
547	=item $AnyEvent::HTTP::MAX_PERSISTENT	896	=item $AnyEvent::HTTP::MAX_PER_HOST
548		897
549	The maximum number of persistent connections to keep open (default: 8).	898	The maximum number of concurrent connections to the same host (identified
		899	by the hostname). If the limit is exceeded, then the additional requests
		900	are queued until previous connections are closed.
550		901
551	Not implemented currently.	902	The default value for this is C<4>, and it is highly advisable to not
552		903	increase it.
553	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
554
555	The maximum time to cache a persistent connection, in seconds (default: 2).
556
557	Not implemented currently.
558		904
559	=item $AnyEvent::HTTP::ACTIVE	905	=item $AnyEvent::HTTP::ACTIVE
560		906
561	The number of active connections. This is not the number of currently	907	The number of active connections. This is not the number of currently
562	running requests, but the number of currently open and non-idle TCP	908	running requests, but the number of currently open and non-idle TCP
…		…
564		910
565	=back	911	=back
566		912
567	=cut	913	=cut
568		914
		915	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		916	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		917
		918	sub format_date($) {
		919	my ($time) = @_;
		920
		921	# RFC 822/1123 format
		922	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		923
		924	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		925	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		926	$H, $M, $S;
		927	}
		928
		929	sub parse_date($) {
		930	my ($date) = @_;
		931
		932	my ($d, $m, $y, $H, $M, $S);
		933
		934	if ($date =~ /^[A-Z][a-z][a-z], ([0-9][0-9]) ([A-Z][a-z][a-z]) ([0-9][0-9][0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) {
		935	# RFC 822/1123, required by RFC 2616
		936	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		937
		938	} elsif ($date =~ /^[A-Z][a-z]+, ([0-9][0-9])-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) {
		939	# RFC 850
		940	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		941
		942	} elsif ($date =~ /^[A-Z][a-z][a-z] ([A-Z][a-z][a-z]) ([0-9 ][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) ([0-9][0-9][0-9][0-9])$/) {
		943	# ISO C's asctime
		944	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		945	}
		946	# other formats fail in the loop below
		947
		948	for (0..11) {
		949	if ($m eq $month[$_]) {
		950	require Time::Local;
		951	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		952	}
		953	}
		954
		955	undef
		956	}
		957
569	sub set_proxy($) {	958	sub set_proxy($) {
		959	if (length $_[0]) {
570	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	960	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		961	or Carp::croak "$_[0]: invalid proxy URL";
		962	$PROXY = [$2, $3 \|\| 3128, $1]
		963	} else {
		964	undef $PROXY;
		965	}
571	}	966	}
572		967
573	# initialise proxy from environment	968	# initialise proxy from environment
		969	eval {
574	set_proxy $ENV{http_proxy};	970	set_proxy $ENV{http_proxy};
		971	};
		972
		973	=head2 SOCKS PROXIES
		974
		975	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		976	compile your perl to support socks, or use an external program such as
		977	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		978	transparently.
		979
		980	Alternatively, for AnyEvent::HTTP only, you can use your own
		981	C<tcp_connect> function that does the proxy handshake - here is an example
		982	that works with socks4a proxies:
		983
		984	use Errno;
		985	use AnyEvent::Util;
		986	use AnyEvent::Socket;
		987	use AnyEvent::Handle;
		988
		989	# host, port and username of/for your socks4a proxy
		990	my $socks_host = "10.0.0.23";
		991	my $socks_port = 9050;
		992	my $socks_user = "";
		993
		994	sub socks4a_connect {
		995	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		996
		997	my $hdl = new AnyEvent::Handle
		998	connect => [$socks_host, $socks_port],
		999	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1000	on_error => sub { $connect_cb->() },
		1001	;
		1002
		1003	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1004
		1005	$hdl->push_read (chunk => 8, sub {
		1006	my ($hdl, $chunk) = @_;
		1007	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1008
		1009	if ($status == 0x5a) {
		1010	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1011	} else {
		1012	$! = Errno::ENXIO; $connect_cb->();
		1013	}
		1014	});
		1015
		1016	$hdl
		1017	}
		1018
		1019	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1020	possibly after switching off other proxy types:
		1021
		1022	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1023
		1024	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1025	my ($data, $headers) = @_;
		1026	...
		1027	};
575		1028
576	=head1 SEE ALSO	1029	=head1 SEE ALSO
577		1030
578	L<AnyEvent>.	1031	L<AnyEvent>.
579		1032
580	=head1 AUTHOR	1033	=head1 AUTHOR
581		1034
582	Marc Lehmann <schmorp@schmorp.de>	1035	Marc Lehmann <schmorp@schmorp.de>
583	http://home.schmorp.de/	1036	http://home.schmorp.de/
584		1037
		1038	With many thanks to Дмитрий Шалашов, who provided countless
		1039	testcases and bugreports.
		1040
585	=cut	1041	=cut
586		1042
587	1	1043	1
588		1044

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.30 by root, Thu Oct 23 02:46:20 2008 UTC vs. Revision 1.66 by root, Fri Dec 31 06:18:30 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.30 by root, Thu Oct 23 02:46:20 2008 UTC vs.
Revision 1.66 by root, Fri Dec 31 06:18:30 2010 UTC