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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.18 by root, Fri Jun 6 16:23:57 2008 UTC vs.
Revision 1.52 by root, Sat Sep 26 10:13:12 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 = '1.01';	53	our $VERSION = '1.43';
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
…		…
71	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
72		72
73	=item http_get $url, key => value..., $cb->($data, $headers)	73	=item http_get $url, key => value..., $cb->($data, $headers)
74		74
75	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
76	additional parameters.	76	additional parameters and the return value.
77		77
78	=item http_head $url, key => value..., $cb->($data, $headers)	78	=item http_head $url, key => value..., $cb->($data, $headers)
79		79
80	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
81	additional parameters.	81	on additional parameters and the return value.
82		82
83	=item http_post $url, $body, key => value..., $cb->($data, $headers)	83	=item http_post $url, $body, key => value..., $cb->($data, $headers)
84		84
85	Executes an HTTP-POST request with a request body of C<$bod>. See the	85	Executes an HTTP-POST request with a request body of C<$body>. See the
86	http_request function for details on additional parameters.	86	http_request function for details on additional parameters and the return
		87	value.
87		88
88	=item http_request $method => $url, key => value..., $cb->($data, $headers)	89	=item http_request $method => $url, key => value..., $cb->($data, $headers)
89		90
90	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL	91	Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
91	must be an absolute http or https URL.	92	must be an absolute http or https URL.
92		93
		94	When called in void context, nothing is returned. In other contexts,
		95	C<http_request> returns a "cancellation guard" - you have to keep the
		96	object at least alive until the callback get called. If the object gets
		97	destroyed before the callbakc is called, the request will be cancelled.
		98
93	The callback will be called with the response data as first argument	99	The callback will be called with the response body data as first argument
94	(or C<undef> if it wasn't available due to errors), and a hash-ref with	100	(or C<undef> if an error occured), and a hash-ref with response headers as
95	response headers as second argument.	101	second argument.
96		102
97	All the headers in that hash are lowercased. In addition to the response	103	All the headers in that hash are lowercased. In addition to the response
98	headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and	104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>
99	C<Reason> contain the three parts of the HTTP Status-Line of the same	105	contain the three parts of the HTTP Status-Line of the same name. The
		106	pseudo-header C<URL> contains the original URL (which can differ from the
		107	requested URL when following redirects).
		108
100	name. If the server sends a header multiple lines, then their contents	109	If the server sends a header multiple times, then their contents will be
101	will be joined together with C<\x00>.	110	joined together with a comma (C<,>), as per the HTTP spec.
102		111
103	If an internal error occurs, such as not being able to resolve a hostname,	112	If an internal error occurs, such as not being able to resolve a hostname,
104	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
105	and the C<Reason> pseudo-header will contain an error message.	114	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		115	message.
106		116
107	A typical callback might look like this:	117	A typical callback might look like this:
108		118
109	sub {	119	sub {
110	my ($body, $hdr) = @_;	120	my ($body, $hdr) = @_;
…		…
128		138
129	=item headers => hashref	139	=item headers => hashref
130		140
131	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
132	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
133	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).
134		146
135	=item timeout => $seconds	147	=item timeout => $seconds
136		148
137	The time-out to use for various stages - each connect attempt will reset	149	The time-out to use for various stages - each connect attempt will reset
138	the timeout, as will read or write activity. Default timeout is 5 minutes.	150	the timeout, as will read or write activity, i.e. this is not an overall
		151	timeout.
		152
		153	Default timeout is 5 minutes.
139		154
140	=item proxy => [$host, $port[, $scheme]] or undef	155	=item proxy => [$host, $port[, $scheme]] or undef
141		156
142	Use the given http proxy for all requests. If not specified, then the	157	Use the given http proxy for all requests. If not specified, then the
143	default proxy (as specified by C<$ENV{http_proxy}>) is used.	158	default proxy (as specified by C<$ENV{http_proxy}>) is used.
144		159
145	C<$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
146	HTTPS.	161	HTTPS.
147		162
148	=item body => $string	163	=item body => $string
149		164
150	The request body, usually empty. Will be-sent as-is (future versions of	165	The request body, usually empty. Will be-sent as-is (future versions of
…		…
156	based on the original netscape specification.	171	based on the original netscape specification.
157		172
158	The C<$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
159	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
160	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
161	recommended, as expire times are currently being ignored.	176	recommended, as expiry times are currently being ignored.
162		177
163	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
164	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
165	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
166	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
167	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.
168		266
169	=back	267	=back
170		268
171	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/
172		270
…		…
185	my ($body, $hdr) = @_;	283	my ($body, $hdr) = @_;
186	use Data::Dumper;	284	use Data::Dumper;
187	print Dumper $hdr;	285	print Dumper $hdr;
188	}	286	}
189	;	287	;
		288
		289	Example: make another simple HTTP GET request, but immediately try to
		290	cancel it.
		291
		292	my $request = http_request GET => "http://www.nethype.de/", sub {
		293	my ($body, $hdr) = @_;
		294	print "$body\n";
		295	};
		296
		297	undef $request;
190		298
191	=cut	299	=cut
192		300
193	sub _slot_schedule;	301	sub _slot_schedule;
194	sub _slot_schedule($) {	302	sub _slot_schedule($) {
…		…
218	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	326	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
219		327
220	_slot_schedule $_[0];	328	_slot_schedule $_[0];
221	}	329	}
222		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
223	sub http_request($$@) {	337	sub http_request($$@) {
224	my $cb = pop;	338	my $cb = pop;
225	my ($method, $url, %arg) = @_;	339	my ($method, $url, %arg) = @_;
226		340
227	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";
228		345
229	$method = uc $method;	346	$method = uc $method;
230		347
231	if (my $hdr = $arg{headers}) {	348	if (my $hdr = $arg{headers}) {
232	while (my ($k, $v) = each %$hdr) {	349	while (my ($k, $v) = each %$hdr) {
233	$hdr{lc $k} = $v;	350	$hdr{lc $k} = $v;
234	}	351	}
235	}	352	}
236		353
237	my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE;	354	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
238		355
239	return $cb->(undef, { Status => 599, Reason => "recursion limit reached" })	356	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })
240	if $recurse < 0;	357	if $recurse < 0;
241		358
242	my $proxy = $arg{proxy} \|\| $PROXY;	359	my $proxy = $arg{proxy} \|\| $PROXY;
243	my $timeout = $arg{timeout} \|\| $TIMEOUT;	360	my $timeout = $arg{timeout} \|\| $TIMEOUT;
244		361
245	$hdr{"user-agent"} \|\|= $USERAGENT;
246
247	my ($scheme, $authority, $upath, $query, $fragment) =	362	my ($uscheme, $uauthority, $upath, $query, $fragment) =
248	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	363	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
249		364
250	$scheme = lc $scheme;	365	$uscheme = lc $uscheme;
251		366
252	my $uport = $scheme eq "http" ? 80	367	my $uport = $uscheme eq "http" ? 80
253	: $scheme eq "https" ? 443	368	: $uscheme eq "https" ? 443
254	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" });	369	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });
255		370
256	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
257
258	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	371	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
259	or return $cb->(undef, { Status => 599, Reason => "unparsable URL" });	372	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });
260		373
261	my $uhost = $1;	374	my $uhost = $1;
262	$uport = $2 if defined $2;	375	$uport = $2 if defined $2;
263		376
		377	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost";
		378
264	$uhost =~ s/^\[(.*)\]$/$1/;	379	$uhost =~ s/^\[(.*)\]$/$1/;
265	$upath .= "?$query" if length $query;	380	$upath .= "?$query" if length $query;
266		381
267	$upath =~ s%^/?%/%;	382	$upath =~ s%^/?%/%;
268		383
269	# cookie processing	384	# cookie processing
270	if (my $jar = $arg{cookie_jar}) {	385	if (my $jar = $arg{cookie_jar}) {
271	%$jar = () if $jar->{version} < 1;	386	%$jar = () if $jar->{version} != 1;
272		387
273	my @cookie;	388	my @cookie;
274		389
275	while (my ($chost, $v) = each %$jar) {	390	while (my ($chost, $v) = each %$jar) {
		391	if ($chost =~ /^\./) {
276	next unless $chost eq substr $uhost, -length $chost;	392	next unless $chost eq substr $uhost, -length $chost;
277	next unless $chost =~ /^\./;	393	} elsif ($chost =~ /\./) {
		394	next unless $chost eq $uhost;
		395	} else {
		396	next;
		397	}
278		398
279	while (my ($cpath, $v) = each %$v) {	399	while (my ($cpath, $v) = each %$v) {
280	next unless $cpath eq substr $upath, 0, length $cpath;	400	next unless $cpath eq substr $upath, 0, length $cpath;
281		401
282	while (my ($k, $v) = each %$v) {	402	while (my ($k, $v) = each %$v) {
283	next if $scheme ne "https" && exists $v->{secure};	403	next if $uscheme ne "https" && exists $v->{secure};
		404	my $value = $v->{value};
		405	$value =~ s/([\\"])/\\$1/g;
284	push @cookie, "$k=$v->{value}";	406	push @cookie, "$k=\"$value\"";
285	}	407	}
286	}	408	}
287	}	409	}
288		410
289	$hdr{cookie} = join "; ", @cookie	411	$hdr{cookie} = join "; ", @cookie
290	if @cookie;	412	if @cookie;
291	}	413	}
292		414
293	my ($rhost, $rport, $rpath); # request host, port, path	415	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
294		416
295	if ($proxy) {	417	if ($proxy) {
296	($rhost, $rport, $scheme) = @$proxy;	418	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
297	$rpath = $url;	419
		420	$rscheme = "http" unless defined $rscheme;
		421
		422	# don't support https requests over https-proxy transport,
		423	# can't be done with tls as spec'ed, unless you double-encrypt.
		424	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
298	} else {	425	} else {
299	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	426	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
300	$hdr{host} = $uhost;
301	}	427	}
		428
		429	# leave out fragment and query string, just a heuristic
		430	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		431	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
302		432
303	$hdr{"content-length"} = length $arg{body};	433	$hdr{"content-length"} = length $arg{body};
304		434
305	my %state = (connect_guard => 1);	435	my %state = (connect_guard => 1);
306		436
…		…
309		439
310	return unless $state{connect_guard};	440	return unless $state{connect_guard};
311		441
312	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	442	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
313	$state{fh} = shift	443	$state{fh} = shift
		444	or do {
		445	my $err = "$!";
		446	%state = ();
314	or return $cb->(undef, { Status => 599, Reason => "$!" });	447	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
		448	};
315		449
316	delete $state{connect_guard}; # reduce memory usage, save a tree	450	pop; # free memory, save a tree
		451
		452	return unless delete $state{connect_guard};
317		453
318	# get handle	454	# get handle
319	$state{handle} = new AnyEvent::Handle	455	$state{handle} = new AnyEvent::Handle
320	fh => $state{fh},	456	fh => $state{fh},
321	($scheme eq "https" ? (tls => "connect") : ());	457	timeout => $timeout,
		458	peername => $rhost,
		459	tls_ctx => $arg{tls_ctx};
322		460
323	# limit the number of persistent connections	461	# limit the number of persistent connections
		462	# keepalive not yet supported
324	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	463	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
325	++$KA_COUNT{$_[1]};	464	++$KA_COUNT{$_[1]};
326	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	465	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		466	--$KA_COUNT{$_[1]}
		467	};
327	$hdr{connection} = "keep-alive";	468	$hdr{connection} = "keep-alive";
328	delete $hdr{connection}; # keep-alive not yet supported
329	} else {	469	} else {
330	delete $hdr{connection};	470	delete $hdr{connection};
331	}	471	}
332		472
333	# (re-)configure handle	473	# (re-)configure handle
334	$state{handle}->timeout ($timeout);
335	$state{handle}->on_error (sub {	474	$state{handle}->on_error (sub {
336	my $errno = "$!";
337	%state = ();	475	%state = ();
338	$cb->(undef, { Status => 599, Reason => $errno });	476	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
339	});	477	});
340	$state{handle}->on_eof (sub {	478	$state{handle}->on_eof (sub {
341	%state = ();	479	%state = ();
342	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file" });	480	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
343	});	481	});
344		482
		483	$state{handle}->starttls ("connect") if $rscheme eq "https";
		484
		485	# handle actual, non-tunneled, request
		486	my $handle_actual_request = sub {
		487	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		488
345	# send request	489	# send request
346	$state{handle}->push_write (	490	$state{handle}->push_write (
347	"$method $rpath HTTP/1.0\015\012"	491	"$method $rpath HTTP/1.0\015\012"
348	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	492	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
349	. "\015\012"	493	. "\015\012"
350	. (delete $arg{body})	494	. (delete $arg{body})
351	);
352
353	%hdr = (); # reduce memory usage, save a kitten
354
355	# status line
356	$state{handle}->push_read (line => qr/\015?\012/, sub {
357	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
358	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));
359
360	my %hdr = ( # response headers
361	HTTPVersion => "\x00$1",
362	Status => "\x00$2",
363	Reason => "\x00$3",
364	);	495	);
365		496
		497	%hdr = (); # reduce memory usage, save a kitten
		498
		499	# status line
		500	$state{handle}->push_read (line => $qr_nl, sub {
		501	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		502	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
		503
		504	my %hdr = ( # response headers
		505	HTTPVersion => ",$1",
		506	Status => ",$2",
		507	Reason => ",$3",
		508	URL => ",$url"
		509	);
		510
366	# headers, could be optimized a bit	511	# headers, could be optimized a bit
367	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	512	$state{handle}->unshift_read (line => $qr_nlnl, sub {
368	for ("$_[1]\012") {	513	for ("$_[1]") {
369	# we support spaces in field names, as lotus domino	514	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
370	# creates them.	515
		516	# things seen, not parsed:
		517	# p3pP="NON CUR OTPi OUR NOR UNI"
		518
371	$hdr{lc $1} .= "\x00$2"	519	$hdr{lc $1} .= ",$2"
372	while /\G	520	while /\G
373	([^:\000-\037]+):	521	([^:\000-\037]*):
374	[\011\040]*	522	[\011\040]*
375	((?: [^\015\012]+ \| \015?\012[\011\040] )*)	523	((?: [^\012]+ \| \012[\011\040] )*)
376	\015?\012	524	\012
377	/gxc;	525	/gxc;
378		526
379	/\G$/	527	/\G$/
380	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" }));	528	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));
381	}	529	}
382		530
383	substr $_, 0, 1, ""	531	substr $_, 0, 1, ""
384	for values %hdr;	532	for values %hdr;
385		533
386	my $finish = sub {	534	# redirect handling
387	%state = ();	535	# microsoft and other shitheads don't give a shit for following standards,
		536	# try to support some common forms of broken Location headers.
		537	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		538	$hdr{location} =~ s/^\.\/+//;
388		539
389	# set-cookie processing	540	my $url = "$rscheme://$uhost:$uport";
390	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {
391	for (split /\x00/, $hdr{"set-cookie"}) {
392	my ($cookie, @arg) = split /;\s*/;
393	my ($name, $value) = split /=/, $cookie, 2;
394	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
395
396	my $cdom = (delete $kv{domain}) \|\| $uhost;
397	my $cpath = (delete $kv{path}) \|\| "/";
398
399	$cdom =~ s/^.?/./; # make sure it starts with a "."
400		541
401	next if $cdom =~ /\.$/;	542	unless ($hdr{location} =~ s/^\///) {
402		543	$url .= $upath;
403	# this is not rfc-like and not netscape-like. go figure.	544	$url =~ s/\/[^\/]*$//;
404	my $ndots = $cdom =~ y/.//;	545	}
405	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	546
406		547	$hdr{location} = "$url/$hdr{location}";
		548	}
		549
		550	my $redirect;
		551
		552	if ($recurse) {
		553	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {
		554	# apparently, mozilla et al. just change POST to GET here
		555	# more research is needed before we do the same
407	# store it	556	$redirect = 1;
408	$arg{cookie_jar}{version} = 1;	557	} elsif ($hdr{Status} == 303) {
409	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	558	# even http/1.1 is unclear on how to mutate the method
		559	$method = "GET" unless $method eq "HEAD";
		560	$redirect = 1;
		561	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {
		562	$redirect = 1;
410	}	563	}
411	}	564	}
412		565
413	if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {	566	my $finish = sub {
414	# microsoft and other assholes don't give a shit for following standards,	567	$state{handle}->destroy if $state{handle};
415	# try to support a common form of broken Location header.	568	%state = ();
416	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
417		569
		570	# set-cookie processing
		571	if ($arg{cookie_jar}) {
		572	for ($_[1]{"set-cookie"}) {
		573	# parse NAME=VALUE
		574	my @kv;
		575
		576	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		577	my $name = $1;
		578	my $value = $3;
		579
		580	unless ($value) {
		581	$value = $2;
		582	$value =~ s/\\(.)/$1/gs;
		583	}
		584
		585	push @kv, $name => $value;
		586
		587	last unless /\G\s*;/gc;
		588	}
		589
		590	last unless @kv;
		591
		592	my $name = shift @kv;
		593	my %kv = (value => shift @kv, @kv);
		594
		595	my $cdom;
		596	my $cpath = (delete $kv{path}) \|\| "/";
		597
		598	if (exists $kv{domain}) {
		599	$cdom = delete $kv{domain};
		600
		601	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		602
		603	next if $cdom =~ /\.$/;
		604
		605	# this is not rfc-like and not netscape-like. go figure.
		606	my $ndots = $cdom =~ y/.//;
		607	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		608	} else {
		609	$cdom = $uhost;
		610	}
		611
		612	# store it
		613	$arg{cookie_jar}{version} = 1;
		614	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		615
		616	redo if /\G\s*,/gc;
		617	}
		618	}
		619
		620	if ($redirect && exists $hdr{location}) {
		621	# we ignore any errors, as it is very common to receive
		622	# Content-Length != 0 but no actual body
		623	# we also access %hdr, as $_[1] might be an erro
418	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	624	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);
		625	} else {
		626	$cb->($_[0], $_[1]);
		627	}
		628	};
		629
		630	my $len = $hdr{"content-length"};
		631
		632	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		633	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
		634	} elsif (
		635	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		636	or $method eq "HEAD"
		637	or (defined $len && !$len)
		638	) {
		639	# no body
		640	$finish->("", \%hdr);
419	} else {	641	} else {
420	$cb->($_[0], $_[1]);	642	# body handling, four different code paths
		643	# for want_body_handle, on_body (2x), normal (2x)
		644	# we might read too much here, but it does not matter yet (no pers. connections)
		645	if (!$redirect && $arg{want_body_handle}) {
		646	$_[0]->on_eof (undef);
		647	$_[0]->on_error (undef);
		648	$_[0]->on_read (undef);
		649
		650	$finish->(delete $state{handle}, \%hdr);
		651
		652	} elsif ($arg{on_body}) {
		653	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		654	if ($len) {
		655	$_[0]->on_eof (undef);
		656	$_[0]->on_read (sub {
		657	$len -= length $_[0]{rbuf};
		658
		659	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		660	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		661
		662	$len > 0
		663	or $finish->("", \%hdr);
		664	});
		665	} else {
		666	$_[0]->on_eof (sub {
		667	$finish->("", \%hdr);
		668	});
		669	$_[0]->on_read (sub {
		670	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		671	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		672	});
		673	}
		674	} else {
		675	$_[0]->on_eof (undef);
		676
		677	if ($len) {
		678	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		679	$_[0]->on_read (sub {
		680	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		681	if $len <= length $_[0]{rbuf};
		682	});
		683	} else {
		684	$_[0]->on_error (sub {
		685	$! == Errno::EPIPE \|\| !$!
		686	? $finish->(delete $_[0]{rbuf}, \%hdr)
		687	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });
		688	});
		689	$_[0]->on_read (sub { });
		690	}
		691	}
421	}	692	}
422	};	693	});
		694	});
		695	};
423		696
424	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	697	# now handle proxy-CONNECT method
425	$finish->(undef, \%hdr);	698	if ($proxy && $uscheme eq "https") {
		699	# oh dear, we have to wrap it into a connect request
		700
		701	# maybe re-use $uauthority with patched port?
		702	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		703	$state{handle}->push_read (line => $qr_nlnl, sub {
		704	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		705	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));
		706
		707	if ($2 == 200) {
		708	$rpath = $upath;
		709	&$handle_actual_request;
426	} else {	710	} else {
427	if (exists $hdr{"content-length"}) {	711	%state = ();
428	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	712	$cb->(undef, { Status => $2, Reason => $3, URL => $url });
429	# could cache persistent connection now
430	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
431	# but we don't, due to misdesigns, this is annoyingly complex
432	};
433
434	$finish->($_[1], \%hdr);
435	});
436	} else {
437	# too bad, need to read until we get an error or EOF,
438	# no way to detect winged data.
439	$_[0]->on_error (sub {
440	$finish->($_[0]{rbuf}, \%hdr);
441	});
442	$_[0]->on_eof (undef);
443	$_[0]->on_read (sub { });
444	}
445	}	713	}
446	});	714	});
		715	} else {
		716	&$handle_actual_request;
447	});	717	}
448	}, sub {	718
449	$timeout	719	}, $arg{on_prepare} \|\| sub { $timeout };
450	};
451	};	720	};
452		721
453	defined wantarray && AnyEvent::Util::guard { %state = () }	722	defined wantarray && AnyEvent::Util::guard { %state = () }
454	}	723	}
455		724
…		…
462	unshift @_, "HEAD";	731	unshift @_, "HEAD";
463	&http_request	732	&http_request
464	}	733	}
465		734
466	sub http_post($$@) {	735	sub http_post($$@) {
		736	my $url = shift;
467	unshift @_, "POST", "body";	737	unshift @_, "POST", $url, "body";
468	&http_request	738	&http_request
469	}	739	}
470		740
471	=back	741	=back
472		742
…		…
475	=over 4	745	=over 4
476		746
477	=item AnyEvent::HTTP::set_proxy "proxy-url"	747	=item AnyEvent::HTTP::set_proxy "proxy-url"
478		748
479	Sets the default proxy server to use. The proxy-url must begin with a	749	Sets the default proxy server to use. The proxy-url must begin with a
480	string of the form C<http://host:port> (optionally C<https:...>).	750	string of the form C<http://host:port> (optionally C<https:...>), croaks
		751	otherwise.
		752
		753	To clear an already-set proxy, use C<undef>.
481		754
482	=item $AnyEvent::HTTP::MAX_RECURSE	755	=item $AnyEvent::HTTP::MAX_RECURSE
483		756
484	The default value for the C<recurse> request parameter (default: C<10>).	757	The default value for the C<recurse> request parameter (default: C<10>).
485		758
486	=item $AnyEvent::HTTP::USERAGENT	759	=item $AnyEvent::HTTP::USERAGENT
487		760
488	The default value for the C<User-Agent> header (the default is	761	The default value for the C<User-Agent> header (the default is
489	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	762	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
490		763
491	=item $AnyEvent::HTTP::MAX_PERSISTENT	764	=item $AnyEvent::HTTP::MAX_PER_HOST
492		765
493	The maximum number of persistent connections to keep open (default: 8).	766	The maximum number of concurrent connections to the same host (identified
		767	by the hostname). If the limit is exceeded, then the additional requests
		768	are queued until previous connections are closed.
494		769
495	Not implemented currently.	770	The default value for this is C<4>, and it is highly advisable to not
496		771	increase it.
497	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
498
499	The maximum time to cache a persistent connection, in seconds (default: 2).
500
501	Not implemented currently.
502		772
503	=item $AnyEvent::HTTP::ACTIVE	773	=item $AnyEvent::HTTP::ACTIVE
504		774
505	The number of active connections. This is not the number of currently	775	The number of active connections. This is not the number of currently
506	running requests, but the number of currently open and non-idle TCP	776	running requests, but the number of currently open and non-idle TCP
…		…
509	=back	779	=back
510		780
511	=cut	781	=cut
512		782
513	sub set_proxy($) {	783	sub set_proxy($) {
		784	if (length $_[0]) {
514	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	785	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		786	or Carp::croak "$_[0]: invalid proxy URL";
		787	$PROXY = [$2, $3 \|\| 3128, $1]
		788	} else {
		789	undef $PROXY;
		790	}
515	}	791	}
516		792
517	# initialise proxy from environment	793	# initialise proxy from environment
		794	eval {
518	set_proxy $ENV{http_proxy};	795	set_proxy $ENV{http_proxy};
		796	};
519		797
520	=head1 SEE ALSO	798	=head1 SEE ALSO
521		799
522	L<AnyEvent>.	800	L<AnyEvent>.
523		801
524	=head1 AUTHOR	802	=head1 AUTHOR
525		803
526	Marc Lehmann <schmorp@schmorp.de>	804	Marc Lehmann <schmorp@schmorp.de>
527	http://home.schmorp.de/	805	http://home.schmorp.de/
528		806
		807	With many thanks to Дмитрий Шалашов, who provided countless
		808	testcases and bugreports.
		809
529	=cut	810	=cut
530		811
531	1	812	1
532		813

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.18 by root, Fri Jun 6 16:23:57 2008 UTC vs. Revision 1.52 by root, Sat Sep 26 10:13:12 2009 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.18 by root, Fri Jun 6 16:23:57 2008 UTC vs.
Revision 1.52 by root, Sat Sep 26 10:13:12 2009 UTC