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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.16 by root, Fri Jun 6 12:57:48 2008 UTC vs.
Revision 1.55 by root, Wed Jun 16 19:17:30 2010 UTC

…		…
3	AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client	3	AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client
4		4
5	=head1 SYNOPSIS	5	=head1 SYNOPSIS
6		6
7	use AnyEvent::HTTP;	7	use AnyEvent::HTTP;
		8
		9	http_get "http://www.nethype.de/", sub { print $_[1] };
		10
		11	# ... do something else here
8		12
9	=head1 DESCRIPTION	13	=head1 DESCRIPTION
10		14
11	This module is an L<AnyEvent> user, you need to make sure that you use and	15	This module is an L<AnyEvent> user, you need to make sure that you use and
12	run a supported event loop.	16	run a supported event loop.
…		…
35	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
36		40
37	use strict;	41	use strict;
38	no warnings;	42	no warnings;
39		43
40	use Carp;	44	use Errno ();
41		45
42	use AnyEvent ();	46	use AnyEvent 5.0 ();
43	use AnyEvent::Util ();	47	use AnyEvent::Util ();
44	use AnyEvent::Socket ();	48	use AnyEvent::Socket ();
45	use AnyEvent::Handle ();	49	use AnyEvent::Handle ();
46		50
47	use base Exporter::;	51	use base Exporter::;
48		52
49	our $VERSION = '1.01';	53	our $VERSION = '1.45';
50		54
51	our @EXPORT = qw(http_get http_request);	55	our @EXPORT = qw(http_get http_post http_head http_request);
52		56
53	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)";
54	our $MAX_RECURSE = 10;	58	our $MAX_RECURSE = 10;
55	our $MAX_PERSISTENT = 8;	59	our $MAX_PERSISTENT = 8;
56	our $PERSISTENT_TIMEOUT = 2;	60	our $PERSISTENT_TIMEOUT = 2;
57	our $TIMEOUT = 300;	61	our $TIMEOUT = 300;
58		62
59	# changing these is evil	63	# changing these is evil
60	our $MAX_PERSISTENT_PER_HOST = 2;	64	our $MAX_PERSISTENT_PER_HOST = 0;
61	our $MAX_PER_HOST = 4;	65	our $MAX_PER_HOST = 4;
62		66
63	our $PROXY;	67	our $PROXY;
64	our $ACTIVE = 0;	68	our $ACTIVE = 0;
65		69
…		…
67	my %CO_SLOT; # number of open connections, and wait queue, per host	71	my %CO_SLOT; # number of open connections, and wait queue, per host
68		72
69	=item http_get $url, key => value..., $cb->($data, $headers)	73	=item http_get $url, key => value..., $cb->($data, $headers)
70		74
71	Executes an HTTP-GET request. See the http_request function for details on	75	Executes an HTTP-GET request. See the http_request function for details on
72	additional parameters.	76	additional parameters and the return value.
73		77
74	=item http_head $url, key => value..., $cb->($data, $headers)	78	=item http_head $url, key => value..., $cb->($data, $headers)
75		79
76	Executes an HTTP-HEAD request. See the http_request function for details on	80	Executes an HTTP-HEAD request. See the http_request function for details
77	additional parameters.	81	on additional parameters and the return value.
78		82
79	=item http_post $url, $body, key => value..., $cb->($data, $headers)	83	=item http_post $url, $body, key => value..., $cb->($data, $headers)
80		84
81	Executes an HTTP-POST request with a request body of C<$bod>. See the	85	Executes an HTTP-POST request with a request body of C<$body>. See the
82	http_request function for details on additional parameters.	86	http_request function for details on additional parameters and the return
		87	value.
83		88
84	=item http_request $method => $url, key => value..., $cb->($data, $headers)	89	=item http_request $method => $url, key => value..., $cb->($data, $headers)
85		90
86	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	91	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
87	must be an absolute http or https URL.	92	must be an absolute http or https URL.
88		93
		94	When called in void context, nothing is returned. In other contexts,
		95	C<http_request> returns a "cancellation guard" - you have to keep the
		96	object at least alive until the callback get called. If the object gets
		97	destroyed before the callbakc is called, the request will be cancelled.
		98
89	The callback will be called with the response data as first argument	99	The callback will be called with the response body data as first argument
90	(or C<undef> if it wasn't available due to errors), and a hash-ref with	100	(or C<undef> if an error occured), and a hash-ref with response headers as
91	response headers as second argument.	101	second argument.
92		102
93	All the headers in that hash are lowercased. In addition to the response	103	All the headers in that hash are lowercased. In addition to the response
94	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	104	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		105	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
95	C<Reason> contain the three parts of the HTTP Status-Line of the same	106	three parts of the HTTP Status-Line of the same name.
		107
		108	The pseudo-header C<URL> contains the actual URL (which can differ from
		109	the requested URL when following redirects - for example, you might get
		110	an error that your URL scheme is not supported even though your URL is a
		111	valid http URL because it redirected to an ftp URL, in which case you can
		112	look at the URL pseudo header).
		113
		114	The pseudo-header C<Redirect> only exists when the request was a result
		115	of an internal redirect. In that case it is an array reference with
		116	the C<($data, $headers)> from the redirect response. Note that this
		117	response could in turn be the result of a redirect itself, and C<<
		118	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		119	response, and so on.
		120
96	name. If the server sends a header multiple lines, then their contents	121	If the server sends a header multiple times, then their contents will be
97	will be joined together with C<\x00>.	122	joined together with a comma (C<,>), as per the HTTP spec.
98		123
99	If an internal error occurs, such as not being able to resolve a hostname,	124	If an internal error occurs, such as not being able to resolve a hostname,
100	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	125	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
101	and the C<Reason> pseudo-header will contain an error message.	126	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		127	message.
102		128
103	A typical callback might look like this:	129	A typical callback might look like this:
104		130
105	sub {	131	sub {
106	my ($body, $hdr) = @_;	132	my ($body, $hdr) = @_;
…		…
124		150
125	=item headers => hashref	151	=item headers => hashref
126		152
127	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
128	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
129	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).
130		158
131	=item timeout => $seconds	159	=item timeout => $seconds
132		160
133	The time-out to use for various stages - each connect attempt will reset	161	The time-out to use for various stages - each connect attempt will reset
134	the timeout, as will read or write activity. Default timeout is 5 minutes.	162	the timeout, as will read or write activity, i.e. this is not an overall
		163	timeout.
		164
		165	Default timeout is 5 minutes.
135		166
136	=item proxy => [$host, $port[, $scheme]] or undef	167	=item proxy => [$host, $port[, $scheme]] or undef
137		168
138	Use the given http proxy for all requests. If not specified, then the	169	Use the given http proxy for all requests. If not specified, then the
139	default proxy (as specified by C<$ENV{http_proxy}>) is used.	170	default proxy (as specified by C<$ENV{http_proxy}>) is used.
140		171
141	C<$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
142	HTTPS.	173	HTTPS.
143		174
144	=item body => $string	175	=item body => $string
145		176
146	The request body, usually empty. Will be-sent as-is (future versions of	177	The request body, usually empty. Will be-sent as-is (future versions of
…		…
152	based on the original netscape specification.	183	based on the original netscape specification.
153		184
154	The C<$hash_ref> must be an (initially empty) hash reference which will	185	The C<$hash_ref> must be an (initially empty) hash reference which will
155	get updated automatically. It is possible to save the cookie_jar to	186	get updated automatically. It is possible to save the cookie_jar to
156	persistent storage with something like JSON or Storable, but this is not	187	persistent storage with something like JSON or Storable, but this is not
157	recommended, as expire times are currently being ignored.	188	recommended, as expiry times are currently being ignored.
158		189
159	Note that this cookie implementation is not of very high quality, nor	190	Note that this cookie implementation is not of very high quality, nor
160	meant to be complete. If you want complete cookie management you have to	191	meant to be complete. If you want complete cookie management you have to
161	do that on your own. C<cookie_jar> is meant as a quick fix to get some	192	do that on your own. C<cookie_jar> is meant as a quick fix to get some
162	cookie-using sites working. Cookies are a privacy disaster, do not use	193	cookie-using sites working. Cookies are a privacy disaster, do not use
163	them unless required to.	194	them unless required to.
		195
		196	=item tls_ctx => $scheme \| $tls_ctx
		197
		198	Specifies the AnyEvent::TLS context to be used for https connections. This
		199	parameter follows the same rules as the C<tls_ctx> parameter to
		200	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		201	C<high> can be specified, which give you a predefined low-security (no
		202	verification, highest compatibility) and high-security (CA and common-name
		203	verification) TLS context.
		204
		205	The default for this option is C<low>, which could be interpreted as "give
		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.
164		278
165	=back	279	=back
166		280
167	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/
168		282
…		…
181	my ($body, $hdr) = @_;	295	my ($body, $hdr) = @_;
182	use Data::Dumper;	296	use Data::Dumper;
183	print Dumper $hdr;	297	print Dumper $hdr;
184	}	298	}
185	;	299	;
		300
		301	Example: make another simple HTTP GET request, but immediately try to
		302	cancel it.
		303
		304	my $request = http_request GET => "http://www.nethype.de/", sub {
		305	my ($body, $hdr) = @_;
		306	print "$body\n";
		307	};
		308
		309	undef $request;
186		310
187	=cut	311	=cut
188		312
189	sub _slot_schedule;	313	sub _slot_schedule;
190	sub _slot_schedule($) {	314	sub _slot_schedule($) {
…		…
214	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	338	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
215		339
216	_slot_schedule $_[0];	340	_slot_schedule $_[0];
217	}	341	}
218		342
		343	our $qr_nl = qr{\015?\012};
		344	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		345
		346	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		347	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		348
219	sub http_request($$@) {	349	sub http_request($$@) {
220	my $cb = pop;	350	my $cb = pop;
221	my ($method, $url, %arg) = @_;	351	my ($method, $url, %arg) = @_;
222		352
223	my %hdr;	353	my %hdr;
		354
		355	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		356	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
224		357
225	$method = uc $method;	358	$method = uc $method;
226		359
227	if (my $hdr = $arg{headers}) {	360	if (my $hdr = $arg{headers}) {
228	while (my ($k, $v) = each %$hdr) {	361	while (my ($k, $v) = each %$hdr) {
229	$hdr{lc $k} = $v;	362	$hdr{lc $k} = $v;
230	}	363	}
231	}	364	}
232		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
233	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	370	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
234		371
235	return $cb->(undef, { Status => 599, Reason => "recursion limit reached" })	372	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
236	if $recurse < 0;	373	if $recurse < 0;
237		374
238	my $proxy = $arg{proxy} \|\| $PROXY;	375	my $proxy = $arg{proxy} \|\| $PROXY;
239	my $timeout = $arg{timeout} \|\| $TIMEOUT;	376	my $timeout = $arg{timeout} \|\| $TIMEOUT;
240		377
241	$hdr{"user-agent"} \|\|= $USERAGENT;
242
243	my ($scheme, $authority, $upath, $query, $fragment) =	378	my ($uscheme, $uauthority, $upath, $query, $fragment) =
244	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	379	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
245		380
246	$scheme = lc $scheme;	381	$uscheme = lc $uscheme;
247		382
248	my $uport = $scheme eq "http" ? 80	383	my $uport = $uscheme eq "http" ? 80
249	: $scheme eq "https" ? 443	384	: $uscheme eq "https" ? 443
250	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" });	385	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });
251		386
252	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
253
254	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	387	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
255	or return $cb->(undef, { Status => 599, Reason => "unparsable URL" });	388	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
256		389
257	my $uhost = $1;	390	my $uhost = $1;
258	$uport = $2 if defined $2;	391	$uport = $2 if defined $2;
259		392
		393	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		394	unless exists $hdr{host};
		395
260	$uhost =~ s/^\[(.*)\]$/$1/;	396	$uhost =~ s/^\[(.*)\]$/$1/;
261	$upath .= "?$query" if length $query;	397	$upath .= "?$query" if length $query;
262		398
263	$upath =~ s%^/?%/%;	399	$upath =~ s%^/?%/%;
264		400
265	# cookie processing	401	# cookie processing
266	if (my $jar = $arg{cookie_jar}) {	402	if (my $jar = $arg{cookie_jar}) {
267	%$jar = () if $jar->{version} < 1;	403	%$jar = () if $jar->{version} != 1;
268		404
269	my @cookie;	405	my @cookie;
270		406
271	while (my ($chost, $v) = each %$jar) {	407	while (my ($chost, $v) = each %$jar) {
		408	if ($chost =~ /^\./) {
272	next unless $chost eq substr $uhost, -length $chost;	409	next unless $chost eq substr $uhost, -length $chost;
273	next unless $chost =~ /^\./;	410	} elsif ($chost =~ /\./) {
		411	next unless $chost eq $uhost;
		412	} else {
		413	next;
		414	}
274		415
275	while (my ($cpath, $v) = each %$v) {	416	while (my ($cpath, $v) = each %$v) {
276	next unless $cpath eq substr $upath, 0, length $cpath;	417	next unless $cpath eq substr $upath, 0, length $cpath;
277		418
278	while (my ($k, $v) = each %$v) {	419	while (my ($k, $v) = each %$v) {
279	next if $scheme ne "https" && exists $v->{secure};	420	next if $uscheme ne "https" && exists $v->{secure};
		421	my $value = $v->{value};
		422	$value =~ s/([\\"])/\\$1/g;
280	push @cookie, "$k=$v->{value}";	423	push @cookie, "$k=\"$value\"";
281	}	424	}
282	}	425	}
283	}	426	}
284		427
285	$hdr{cookie} = join "; ", @cookie	428	$hdr{cookie} = join "; ", @cookie
286	if @cookie;	429	if @cookie;
287	}	430	}
288		431
289	my ($rhost, $rport, $rpath); # request host, port, path	432	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
290		433
291	if ($proxy) {	434	if ($proxy) {
292	($rhost, $rport, $scheme) = @$proxy;	435	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
293	$rpath = $url;	436
		437	$rscheme = "http" unless defined $rscheme;
		438
		439	# don't support https requests over https-proxy transport,
		440	# can't be done with tls as spec'ed, unless you double-encrypt.
		441	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
294	} else {	442	} else {
295	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	443	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
296	$hdr{host} = $uhost;
297	}	444	}
298		445
		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
299	$hdr{"content-length"} = length $arg{body};	450	$hdr{"content-length"} = length $arg{body}
		451	if length $arg{body} \|\| $method ne "GET";
300		452
301	my %state = (connect_guard => 1);	453	my %state = (connect_guard => 1);
302		454
303	_get_slot $uhost, sub {	455	_get_slot $uhost, sub {
304	$state{slot_guard} = shift;	456	$state{slot_guard} = shift;
305		457
306	return unless $state{connect_guard};	458	return unless $state{connect_guard};
307		459
308	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	460	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
309	$state{fh} = shift	461	$state{fh} = shift
		462	or do {
		463	my $err = "$!";
		464	%state = ();
310	or return $cb->(undef, { Status => 599, Reason => "$!" });	465	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		466	};
311		467
312	delete $state{connect_guard}; # reduce memory usage, save a tree	468	pop; # free memory, save a tree
		469
		470	return unless delete $state{connect_guard};
313		471
314	# get handle	472	# get handle
315	$state{handle} = new AnyEvent::Handle	473	$state{handle} = new AnyEvent::Handle
316	fh => $state{fh},	474	fh => $state{fh},
317	($scheme eq "https" ? (tls => "connect") : ());	475	timeout => $timeout,
		476	peername => $rhost,
		477	tls_ctx => $arg{tls_ctx};
318		478
319	# limit the number of persistent connections	479	# limit the number of persistent connections
		480	# keepalive not yet supported
320	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	481	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
321	++$KA_COUNT{$_[1]};	482	++$KA_COUNT{$_[1]};
322	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	483	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		484	--$KA_COUNT{$_[1]}
		485	};
323	$hdr{connection} = "keep-alive";	486	$hdr{connection} = "keep-alive";
324	delete $hdr{connection}; # keep-alive not yet supported
325	} else {	487	} else {
326	delete $hdr{connection};	488	delete $hdr{connection};
327	}	489	}
328		490
329	# (re-)configure handle	491	# (re-)configure handle
330	$state{handle}->timeout ($timeout);
331	$state{handle}->on_error (sub {	492	$state{handle}->on_error (sub {
332	my $errno = "$!";
333	%state = ();	493	%state = ();
334	$cb->(undef, { Status => 599, Reason => $errno });	494	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
335	});	495	});
336	$state{handle}->on_eof (sub {	496	$state{handle}->on_eof (sub {
337	%state = ();	497	%state = ();
338	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });	498	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
339	});	499	});
340		500
		501	$state{handle}->starttls ("connect") if $rscheme eq "https";
		502
		503	# handle actual, non-tunneled, request
		504	my $handle_actual_request = sub {
		505	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		506
341	# send request	507	# send request
342	$state{handle}->push_write (	508	$state{handle}->push_write (
343	"$method $rpath HTTP/1.0\015\012"	509	"$method $rpath HTTP/1.0\015\012"
344	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	510	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
345	. "\015\012"	511	. "\015\012"
346	. (delete $arg{body})	512	. (delete $arg{body})
347	);
348
349	%hdr = (); # reduce memory usage, save a kitten
350
351	# status line
352	$state{handle}->push_read (line => qr/\015?\012/, sub {
353	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
354	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));
355
356	my %hdr = ( # response headers
357	HTTPVersion => "\x00$1",
358	Status => "\x00$2",
359	Reason => "\x00$3",
360	);	513	);
361		514
		515	# return if error occured during push_write()
		516	return unless %state;
		517
		518	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		519
		520	# status line
		521	$state{handle}->push_read (line => $qr_nl, sub {
		522	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		523	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", @pseudo }));
		524
		525	push @pseudo,
		526	HTTPVersion => $1,
		527	Status => $2,
		528	Reason => $3,
		529	;
		530
362	# headers, could be optimized a bit	531	# headers, could be optimized a bit
363	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	532	$state{handle}->unshift_read (line => $qr_nlnl, sub {
364	for ("$_[1]\012") {	533	for ("$_[1]") {
365	# we support spaces in field names, as lotus domino	534	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
366	# creates them.	535
		536	# things seen, not parsed:
		537	# p3pP="NON CUR OTPi OUR NOR UNI"
		538
367	$hdr{lc $1} .= "\x00$2"	539	$hdr{lc $1} .= ",$2"
368	while /\G	540	while /\G
369	([^:\000-\037]+):	541	([^:\000-\037]*):
370	[\011\040]*	542	[\011\040]*
371	((?: [^\015\012]+ \| \015?\012[\011\040] )*)	543	((?: [^\012]+ \| \012[\011\040] )*)
372	\015?\012	544	\012
373	/gxc;	545	/gxc;
374		546
375	/\G$/	547	/\G$/
376	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" }));	548	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
377	}	549	}
378		550
		551	# remove the "," prefix we added to all headers above
379	substr $_, 0, 1, ""	552	substr $_, 0, 1, ""
380	for values %hdr;	553	for values %hdr;
381		554
382	my $finish = sub {	555	# patch in all pseudo headers
383	%state = ();	556	%hdr = (%hdr, @pseudo);
384		557
385	# set-cookie processing	558	# redirect handling
386	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {	559	# microsoft and other shitheads don't give a shit for following standards,
387	for (split /\x00/, $hdr{"set-cookie"}) {	560	# try to support some common forms of broken Location headers.
388	my ($cookie, @arg) = split /;\s*/;	561	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
389	my ($name, $value) = split /=/, $cookie, 2;	562	$hdr{location} =~ s/^\.\/+//;
390	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
391
392	my $cdom = (delete $kv{domain}) \|\| $uhost;
393	my $cpath = (delete $kv{path}) \|\| "/";
394
395	$cdom =~ s/^.?/./; # make sure it starts with a "."
396		563
397	next if $cdom =~ /\.$/;	564	my $url = "$rscheme://$uhost:$uport";
398		565
399	# this is not rfc-like and not netscape-like. go figure.	566	unless ($hdr{location} =~ s/^\///) {
400	my $ndots = $cdom =~ y/.//;	567	$url .= $upath;
401	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	568	$url =~ s/\/[^\/]*$//;
402		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
403	# store it	582	$redirect = 1;
404	$arg{cookie_jar}{version} = 1;	583	} elsif ($status == 303) {
405	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	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	$redirect = 1;
406	}	589	}
407	}	590	}
408		591
409	if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {	592	my $finish = sub {
410	# microsoft and other assholes don't give a shit for following standards,	593	$state{handle}->destroy if $state{handle};
411	# try to support a common form of broken Location header.	594	%state = ();
412	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
413		595
414	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	596	# set-cookie processing
		597	if ($arg{cookie_jar}) {
		598	for ($_[1]{"set-cookie"}) {
		599	# parse NAME=VALUE
		600	my @kv;
		601
		602	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		603	my $name = $1;
		604	my $value = $3;
		605
		606	unless ($value) {
		607	$value = $2;
		608	$value =~ s/\\(.)/$1/gs;
		609	}
		610
		611	push @kv, $name => $value;
		612
		613	last unless /\G\s*;/gc;
		614	}
		615
		616	last unless @kv;
		617
		618	my $name = shift @kv;
		619	my %kv = (value => shift @kv, @kv);
		620
		621	my $cdom;
		622	my $cpath = (delete $kv{path}) \|\| "/";
		623
		624	if (exists $kv{domain}) {
		625	$cdom = delete $kv{domain};
		626
		627	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		628
		629	next if $cdom =~ /\.$/;
		630
		631	# this is not rfc-like and not netscape-like. go figure.
		632	my $ndots = $cdom =~ y/.//;
		633	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		634	} else {
		635	$cdom = $uhost;
		636	}
		637
		638	# store it
		639	$arg{cookie_jar}{version} = 1;
		640	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		641
		642	redo if /\G\s*,/gc;
		643	}
		644	}
		645
		646	if ($redirect && exists $hdr{location}) {
		647	# we ignore any errors, as it is very common to receive
		648	# Content-Length != 0 but no actual body
		649	# we also access %hdr, as $_[1] might be an erro
		650	http_request (
		651	$method => $hdr{location},
		652	%arg,
		653	recurse => $recurse - 1,
		654	Redirect => \@_,
		655	$cb);
		656	} else {
		657	$cb->($_[0], $_[1]);
		658	}
		659	};
		660
		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
		671	$finish->("", \%hdr);
415	} else {	672	} else {
416	$cb->($_[0], $_[1]);	673	# body handling, four different code paths
		674	# for want_body_handle, on_body (2x), normal (2x)
		675	# we might read too much here, but it does not matter yet (no pers. connections)
		676	if (!$redirect && $arg{want_body_handle}) {
		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);
		695	});
		696	} else {
		697	$_[0]->on_eof (sub {
		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	});
		704	}
		705	} else {
		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	});
		720	$_[0]->on_read (sub { });
		721	}
		722	}
417	}	723	}
418	};	724	});
		725	});
		726	};
419		727
420	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	728	# now handle proxy-CONNECT method
421	$finish->(undef, \%hdr);	729	if ($proxy && $uscheme eq "https") {
		730	# oh dear, we have to wrap it into a connect request
		731
		732	# maybe re-use $uauthority with patched port?
		733	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		734	$state{handle}->push_read (line => $qr_nlnl, sub {
		735	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		736	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
		737
		738	if ($2 == 200) {
		739	$rpath = $upath;
		740	&$handle_actual_request;
422	} else {	741	} else {
423	if (exists $hdr{"content-length"}) {	742	%state = ();
424	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	743	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
425	# could cache persistent connection now
426	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
427	# but we don't, due to misdesigns, this is annoyingly complex
428	};
429
430	$finish->($_[1], \%hdr);
431	});
432	} else {
433	# too bad, need to read until we get an error or EOF,
434	# no way to detect winged data.
435	$_[0]->on_error (sub {
436	$finish->($_[0]{rbuf}, \%hdr);
437	});
438	$_[0]->on_eof (undef);
439	$_[0]->on_read (sub { });
440	}
441	}	744	}
442	});	745	});
		746	} else {
		747	&$handle_actual_request;
443	});	748	}
444	}, sub {	749
445	$timeout	750	}, $arg{on_prepare} \|\| sub { $timeout };
446	};
447	};	751	};
448		752
449	defined wantarray && AnyEvent::Util::guard { %state = () }	753	defined wantarray && AnyEvent::Util::guard { %state = () }
450	}	754	}
451		755
…		…
458	unshift @_, "HEAD";	762	unshift @_, "HEAD";
459	&http_request	763	&http_request
460	}	764	}
461		765
462	sub http_post($$@) {	766	sub http_post($$@) {
		767	my $url = shift;
463	unshift @_, "POST", "body";	768	unshift @_, "POST", $url, "body";
464	&http_request	769	&http_request
465	}	770	}
466		771
467	=back	772	=back
468		773
		774	=head2 DNS CACHING
		775
		776	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		777	the actual connection, which in turn uses AnyEvent::DNS to resolve
		778	hostnames. The latter is a simple stub resolver and does no caching
		779	on its own. If you want DNS caching, you currently have to provide
		780	your own default resolver (by storing a suitable resolver object in
		781	C<$AnyEvent::DNS::RESOLVER>).
		782
469	=head2 GLOBAL FUNCTIONS AND VARIABLES	783	=head2 GLOBAL FUNCTIONS AND VARIABLES
470		784
471	=over 4	785	=over 4
472		786
473	=item AnyEvent::HTTP::set_proxy "proxy-url"	787	=item AnyEvent::HTTP::set_proxy "proxy-url"
474		788
475	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
476	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>.
477		794
478	=item $AnyEvent::HTTP::MAX_RECURSE	795	=item $AnyEvent::HTTP::MAX_RECURSE
479		796
480	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>).
481		798
482	=item $AnyEvent::HTTP::USERAGENT	799	=item $AnyEvent::HTTP::USERAGENT
483		800
484	The default value for the C<User-Agent> header (the default is	801	The default value for the C<User-Agent> header (the default is
485	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	802	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
486		803
487	=item $AnyEvent::HTTP::MAX_PERSISTENT	804	=item $AnyEvent::HTTP::MAX_PER_HOST
488		805
489	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.
490		809
491	Not implemented currently.	810	The default value for this is C<4>, and it is highly advisable to not
492		811	increase it.
493	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
494
495	The maximum time to cache a persistent connection, in seconds (default: 2).
496
497	Not implemented currently.
498		812
499	=item $AnyEvent::HTTP::ACTIVE	813	=item $AnyEvent::HTTP::ACTIVE
500		814
501	The number of active connections. This is not the number of currently	815	The number of active connections. This is not the number of currently
502	running requests, but the number of currently open and non-idle TCP	816	running requests, but the number of currently open and non-idle TCP
…		…
505	=back	819	=back
506		820
507	=cut	821	=cut
508		822
509	sub set_proxy($) {	823	sub set_proxy($) {
		824	if (length $_[0]) {
510	$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	}
511	}	831	}
512		832
513	# initialise proxy from environment	833	# initialise proxy from environment
		834	eval {
514	set_proxy $ENV{http_proxy};	835	set_proxy $ENV{http_proxy};
		836	};
515		837
516	=head1 SEE ALSO	838	=head1 SEE ALSO
517		839
518	L<AnyEvent>.	840	L<AnyEvent>.
519		841
520	=head1 AUTHOR	842	=head1 AUTHOR
521		843
522	Marc Lehmann <schmorp@schmorp.de>	844	Marc Lehmann <schmorp@schmorp.de>
523	http://home.schmorp.de/	845	http://home.schmorp.de/
		846
		847	With many thanks to Дмитрий Шалашов, who provided countless
		848	testcases and bugreports.
524		849
525	=cut	850	=cut
526		851
527	1	852	1
528		853

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.16 by root, Fri Jun 6 12:57:48 2008 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 1.16 by root, Fri Jun 6 12:57:48 2008 UTC vs.
Revision 1.55 by root, Wed Jun 16 19:17:30 2010 UTC