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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.24 by root, Wed Jul 2 01:30:33 2008 UTC vs.
Revision 1.54 by root, Wed Jun 16 18:09:52 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 ();	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 = '1.03';	53	our $VERSION = '1.44';
54		54
55	our @EXPORT = qw(http_get http_post http_head http_request);	55	our @EXPORT = qw(http_get http_post http_head http_request);
56		56
57	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	57	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58	our $MAX_RECURSE = 10;	58	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;	59	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	60	our $PERSISTENT_TIMEOUT = 2;
61	our $TIMEOUT = 300;	61	our $TIMEOUT = 300;
62		62
63	# changing these is evil	63	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 2;	64	our $MAX_PERSISTENT_PER_HOST = 0;
65	our $MAX_PER_HOST = 4;	65	our $MAX_PER_HOST = 4;
66		66
67	our $PROXY;	67	our $PROXY;
68	our $ACTIVE = 0;	68	our $ACTIVE = 0;
69		69
…		…
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<$method> (e.g. C<GET>, C<POST>). The URL
91	must be an absolute http or https URL.	92	must be an absolute http or https URL.
92		93
		94	When called in void context, nothing is returned. In other contexts,
		95	C<http_request> returns a "cancellation guard" - you have to keep the
		96	object at least alive until the callback get called. If the object gets
		97	destroyed before the callbakc is called, the request will be cancelled.
		98
93	The callback will be called with the response data as first argument	99	The callback will be called with the response body data as first argument
94	(or C<undef> if it wasn't available due to errors), and a hash-ref with	100	(or C<undef> if an error occured), and a hash-ref with response headers as
95	response headers as second argument.	101	second argument.
96		102
97	All the headers in that hash are lowercased. In addition to the response	103	All the headers in that hash are lowercased. In addition to the response
98	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>
99	contain the three parts of the HTTP Status-Line of the same name. The	105	contain the three parts of the HTTP Status-Line of the same name. The
100	pseudo-header C<URL> contains the original URL (which can differ from the	106	pseudo-header C<URL> contains the original URL (which can differ from the
101	requested URL when following redirects).	107	requested URL when following redirects).
102		108
103	If the server sends a header multiple lines, then their contents will be	109	If the server sends a header multiple times, then their contents will be
104	joined together with C<\x00>.	110	joined together with a comma (C<,>), as per the HTTP spec.
105		111
106	If an internal error occurs, such as not being able to resolve a hostname,	112	If an internal error occurs, such as not being able to resolve a hostname,
107	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
108	and the C<Reason> pseudo-header will contain an error message.	114	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		115	message.
109		116
110	A typical callback might look like this:	117	A typical callback might look like this:
111		118
112	sub {	119	sub {
113	my ($body, $hdr) = @_;	120	my ($body, $hdr) = @_;
…		…
131		138
132	=item headers => hashref	139	=item headers => hashref
133		140
134	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
135	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
136	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).
137		146
138	=item timeout => $seconds	147	=item timeout => $seconds
139		148
140	The time-out to use for various stages - each connect attempt will reset	149	The time-out to use for various stages - each connect attempt will reset
141	the timeout, as will read or write activity. Default timeout is 5 minutes.	150	the timeout, as will read or write activity, i.e. this is not an overall
		151	timeout.
		152
		153	Default timeout is 5 minutes.
142		154
143	=item proxy => [$host, $port[, $scheme]] or undef	155	=item proxy => [$host, $port[, $scheme]] or undef
144		156
145	Use the given http proxy for all requests. If not specified, then the	157	Use the given http proxy for all requests. If not specified, then the
146	default proxy (as specified by C<$ENV{http_proxy}>) is used.	158	default proxy (as specified by C<$ENV{http_proxy}>) is used.
147		159
148	C<$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
149	HTTPS.	161	HTTPS.
150		162
151	=item body => $string	163	=item body => $string
152		164
153	The request body, usually empty. Will be-sent as-is (future versions of	165	The request body, usually empty. Will be-sent as-is (future versions of
…		…
159	based on the original netscape specification.	171	based on the original netscape specification.
160		172
161	The C<$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
162	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
163	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
164	recommended, as expire times are currently being ignored.	176	recommended, as expiry times are currently being ignored.
165		177
166	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
167	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
168	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
169	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
170	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.
171		266
172	=back	267	=back
173		268
174	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/
175		270
…		…
188	my ($body, $hdr) = @_;	283	my ($body, $hdr) = @_;
189	use Data::Dumper;	284	use Data::Dumper;
190	print Dumper $hdr;	285	print Dumper $hdr;
191	}	286	}
192	;	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 $request;
193		298
194	=cut	299	=cut
195		300
196	sub _slot_schedule;	301	sub _slot_schedule;
197	sub _slot_schedule($) {	302	sub _slot_schedule($) {
…		…
221	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	326	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
222		327
223	_slot_schedule $_[0];	328	_slot_schedule $_[0];
224	}	329	}
225		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
226	sub http_request($$@) {	337	sub http_request($$@) {
227	my $cb = pop;	338	my $cb = pop;
228	my ($method, $url, %arg) = @_;	339	my ($method, $url, %arg) = @_;
229		340
230	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";
231		345
232	$method = uc $method;	346	$method = uc $method;
233		347
234	if (my $hdr = $arg{headers}) {	348	if (my $hdr = $arg{headers}) {
235	while (my ($k, $v) = each %$hdr) {	349	while (my ($k, $v) = each %$hdr) {
…		…
237	}	351	}
238	}	352	}
239		353
240	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	354	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
241		355
242	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	356	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })
243	if $recurse < 0;	357	if $recurse < 0;
244		358
245	my $proxy = $arg{proxy} \|\| $PROXY;	359	my $proxy = $arg{proxy} \|\| $PROXY;
246	my $timeout = $arg{timeout} \|\| $TIMEOUT;	360	my $timeout = $arg{timeout} \|\| $TIMEOUT;
247		361
248	$hdr{"user-agent"} \|\|= $USERAGENT;
249
250	my ($scheme, $authority, $upath, $query, $fragment) =	362	my ($uscheme, $uauthority, $upath, $query, $fragment) =
251	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	363	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;
252		364
253	$scheme = lc $scheme;	365	$uscheme = lc $uscheme;
254		366
255	my $uport = $scheme eq "http" ? 80	367	my $uport = $uscheme eq "http" ? 80
256	: $scheme eq "https" ? 443	368	: $uscheme eq "https" ? 443
257	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	369	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });
258		370
259	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
260
261	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	371	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
262	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	372	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });
263		373
264	my $uhost = $1;	374	my $uhost = $1;
265	$uport = $2 if defined $2;	375	$uport = $2 if defined $2;
266		376
		377	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		378	unless exists $hdr{host};
		379
267	$uhost =~ s/^\[(.*)\]$/$1/;	380	$uhost =~ s/^\[(.*)\]$/$1/;
268	$upath .= "?$query" if length $query;	381	$upath .= "?$query" if length $query;
269		382
270	$upath =~ s%^/?%/%;	383	$upath =~ s%^/?%/%;
271		384
272	# cookie processing	385	# cookie processing
273	if (my $jar = $arg{cookie_jar}) {	386	if (my $jar = $arg{cookie_jar}) {
274	%$jar = () if $jar->{version} < 1;	387	%$jar = () if $jar->{version} != 1;
275		388
276	my @cookie;	389	my @cookie;
277		390
278	while (my ($chost, $v) = each %$jar) {	391	while (my ($chost, $v) = each %$jar) {
		392	if ($chost =~ /^\./) {
279	next unless $chost eq substr $uhost, -length $chost;	393	next unless $chost eq substr $uhost, -length $chost;
280	next unless $chost =~ /^\./;	394	} elsif ($chost =~ /\./) {
		395	next unless $chost eq $uhost;
		396	} else {
		397	next;
		398	}
281		399
282	while (my ($cpath, $v) = each %$v) {	400	while (my ($cpath, $v) = each %$v) {
283	next unless $cpath eq substr $upath, 0, length $cpath;	401	next unless $cpath eq substr $upath, 0, length $cpath;
284		402
285	while (my ($k, $v) = each %$v) {	403	while (my ($k, $v) = each %$v) {
286	next if $scheme ne "https" && exists $v->{secure};	404	next if $uscheme ne "https" && exists $v->{secure};
		405	my $value = $v->{value};
		406	$value =~ s/([\\"])/\\$1/g;
287	push @cookie, "$k=$v->{value}";	407	push @cookie, "$k=\"$value\"";
288	}	408	}
289	}	409	}
290	}	410	}
291		411
292	$hdr{cookie} = join "; ", @cookie	412	$hdr{cookie} = join "; ", @cookie
293	if @cookie;	413	if @cookie;
294	}	414	}
295		415
296	my ($rhost, $rport, $rpath); # request host, port, path	416	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
297		417
298	if ($proxy) {	418	if ($proxy) {
299	($rhost, $rport, $scheme) = @$proxy;	419	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
300	$rpath = $url;	420
		421	$rscheme = "http" unless defined $rscheme;
		422
		423	# don't support https requests over https-proxy transport,
		424	# can't be done with tls as spec'ed, unless you double-encrypt.
		425	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
301	} else {	426	} else {
302	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	427	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
303	$hdr{host} = $uhost;
304	}	428	}
305		429
		430	# leave out fragment and query string, just a heuristic
		431	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		432	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		433
306	$hdr{"content-length"} = length $arg{body};	434	$hdr{"content-length"} = length $arg{body}
		435	if length $arg{body} \|\| $method ne "GET";
307		436
308	my %state = (connect_guard => 1);	437	my %state = (connect_guard => 1);
309		438
310	_get_slot $uhost, sub {	439	_get_slot $uhost, sub {
311	$state{slot_guard} = shift;	440	$state{slot_guard} = shift;
312		441
313	return unless $state{connect_guard};	442	return unless $state{connect_guard};
314		443
315	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	444	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
316	$state{fh} = shift	445	$state{fh} = shift
		446	or do {
		447	my $err = "$!";
		448	%state = ();
317	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	449	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });
		450	};
318		451
319	delete $state{connect_guard}; # reduce memory usage, save a tree	452	pop; # free memory, save a tree
		453
		454	return unless delete $state{connect_guard};
320		455
321	# get handle	456	# get handle
322	$state{handle} = new AnyEvent::Handle	457	$state{handle} = new AnyEvent::Handle
323	fh => $state{fh},	458	fh => $state{fh},
324	($scheme eq "https" ? (tls => "connect") : ());	459	timeout => $timeout,
		460	peername => $rhost,
		461	tls_ctx => $arg{tls_ctx};
325		462
326	# limit the number of persistent connections	463	# limit the number of persistent connections
		464	# keepalive not yet supported
327	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	465	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
328	++$KA_COUNT{$_[1]};	466	++$KA_COUNT{$_[1]};
329	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };	467	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		468	--$KA_COUNT{$_[1]}
		469	};
330	$hdr{connection} = "keep-alive";	470	$hdr{connection} = "keep-alive";
331	delete $hdr{connection}; # keep-alive not yet supported
332	} else {	471	} else {
333	delete $hdr{connection};	472	delete $hdr{connection};
334	}	473	}
335		474
336	# (re-)configure handle	475	# (re-)configure handle
337	$state{handle}->timeout ($timeout);
338	$state{handle}->on_error (sub {	476	$state{handle}->on_error (sub {
339	my $errno = "$!";
340	%state = ();	477	%state = ();
341	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });	478	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
342	});	479	});
343	$state{handle}->on_eof (sub {	480	$state{handle}->on_eof (sub {
344	%state = ();	481	%state = ();
345	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });	482	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
346	});	483	});
347		484
		485	$state{handle}->starttls ("connect") if $rscheme eq "https";
		486
		487	# handle actual, non-tunneled, request
		488	my $handle_actual_request = sub {
		489	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		490
348	# send request	491	# send request
349	$state{handle}->push_write (	492	$state{handle}->push_write (
350	"$method $rpath HTTP/1.0\015\012"	493	"$method $rpath HTTP/1.0\015\012"
351	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)	494	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
352	. "\015\012"	495	. "\015\012"
353	. (delete $arg{body})	496	. (delete $arg{body})
354	);
355
356	%hdr = (); # reduce memory usage, save a kitten
357
358	# status line
359	$state{handle}->push_read (line => qr/\015?\012/, sub {
360	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
361	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
362
363	my %hdr = ( # response headers
364	HTTPVersion => "\x00$1",
365	Status => "\x00$2",
366	Reason => "\x00$3",
367	URL => "\x00$url"
368	);	497	);
369		498
		499	# return if error occured during push_write()
		500	return unless %state;
		501
		502	%hdr = (); # reduce memory usage, save a kitten
		503
		504	# status line
		505	$state{handle}->push_read (line => $qr_nl, sub {
		506	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		507	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
		508
		509	my %hdr = ( # response headers
		510	HTTPVersion => ",$1",
		511	Status => ",$2",
		512	Reason => ",$3",
		513	URL => ",$url"
		514	);
		515
370	# headers, could be optimized a bit	516	# headers, could be optimized a bit
371	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {	517	$state{handle}->unshift_read (line => $qr_nlnl, sub {
372	for ("$_[1]\012") {	518	for ("$_[1]") {
373	# we support spaces in field names, as lotus domino	519	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
374	# creates them.	520
		521	# things seen, not parsed:
		522	# p3pP="NON CUR OTPi OUR NOR UNI"
		523
375	$hdr{lc $1} .= "\x00$2"	524	$hdr{lc $1} .= ",$2"
376	while /\G	525	while /\G
377	([^:\000-\037]+):	526	([^:\000-\037]*):
378	[\011\040]*	527	[\011\040]*
379	((?: [^\015\012]+ \| \015?\012[\011\040] )*)	528	((?: [^\012]+ \| \012[\011\040] )*)
380	\015?\012	529	\012
381	/gxc;	530	/gxc;
382		531
383	/\G$/	532	/\G$/
384	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));	533	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));
385	}	534	}
386		535
387	substr $_, 0, 1, ""	536	substr $_, 0, 1, ""
388	for values %hdr;	537	for values %hdr;
389		538
390	my $finish = sub {	539	# redirect handling
391	%state = ();	540	# microsoft and other shitheads don't give a shit for following standards,
		541	# try to support some common forms of broken Location headers.
		542	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		543	$hdr{location} =~ s/^\.\/+//;
392		544
393	# set-cookie processing	545	my $url = "$rscheme://$uhost:$uport";
394	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {
395	for (split /\x00/, $hdr{"set-cookie"}) {
396	my ($cookie, @arg) = split /;\s*/;
397	my ($name, $value) = split /=/, $cookie, 2;
398	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
399
400	my $cdom = (delete $kv{domain}) \|\| $uhost;
401	my $cpath = (delete $kv{path}) \|\| "/";
402
403	$cdom =~ s/^.?/./; # make sure it starts with a "."
404		546
405	next if $cdom =~ /\.$/;	547	unless ($hdr{location} =~ s/^\///) {
406		548	$url .= $upath;
407	# this is not rfc-like and not netscape-like. go figure.	549	$url =~ s/\/[^\/]*$//;
408	my $ndots = $cdom =~ y/.//;	550	}
409	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	551
410		552	$hdr{location} = "$url/$hdr{location}";
		553	}
		554
		555	my $redirect;
		556
		557	if ($recurse) {
		558	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {
		559	# apparently, mozilla et al. just change POST to GET here
		560	# more research is needed before we do the same
411	# store it	561	$redirect = 1;
412	$arg{cookie_jar}{version} = 1;	562	} elsif ($hdr{Status} == 303) {
413	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	563	# even http/1.1 is unclear on how to mutate the method
		564	$method = "GET" unless $method eq "HEAD";
		565	$redirect = 1;
		566	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {
		567	$redirect = 1;
414	}	568	}
415	}	569	}
416		570
417	# microsoft and other assholes don't give a shit for following standards,	571	my $finish = sub {
418	# try to support a common form of broken Location header.	572	$state{handle}->destroy if $state{handle};
419	$_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%	573	%state = ();
		574
		575	# set-cookie processing
		576	if ($arg{cookie_jar}) {
		577	for ($_[1]{"set-cookie"}) {
		578	# parse NAME=VALUE
		579	my @kv;
		580
		581	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		582	my $name = $1;
		583	my $value = $3;
		584
		585	unless ($value) {
		586	$value = $2;
		587	$value =~ s/\\(.)/$1/gs;
		588	}
		589
		590	push @kv, $name => $value;
		591
		592	last unless /\G\s*;/gc;
		593	}
		594
		595	last unless @kv;
		596
		597	my $name = shift @kv;
		598	my %kv = (value => shift @kv, @kv);
		599
		600	my $cdom;
		601	my $cpath = (delete $kv{path}) \|\| "/";
		602
		603	if (exists $kv{domain}) {
		604	$cdom = delete $kv{domain};
		605
		606	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		607
		608	next if $cdom =~ /\.$/;
		609
		610	# this is not rfc-like and not netscape-like. go figure.
		611	my $ndots = $cdom =~ y/.//;
		612	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		613	} else {
		614	$cdom = $uhost;
		615	}
		616
		617	# store it
		618	$arg{cookie_jar}{version} = 1;
		619	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		620
		621	redo if /\G\s*,/gc;
		622	}
		623	}
		624
420	if exists $_[1]{location};	625	if ($redirect && exists $hdr{location}) {
421		626	# we ignore any errors, as it is very common to receive
422	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {	627	# Content-Length != 0 but no actual body
423	# apparently, mozilla et al. just change POST to GET here	628	# we also access %hdr, as $_[1] might be an erro
424	# more research is needed before we do the same
425	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
426	} elsif ($_[1]{Status} == 303 && $recurse) {
427	# even http/1.1 is unlear on how to mutate the method
428	$method = "GET" unless $method eq "HEAD";
429	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	629	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);
430	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {	630	} else {
431	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	631	$cb->($_[0], $_[1]);
		632	}
		633	};
		634
		635	my $len = $hdr{"content-length"};
		636
		637	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		638	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
		639	} elsif (
		640	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		641	or $method eq "HEAD"
		642	or (defined $len && !$len)
		643	) {
		644	# no body
		645	$finish->("", \%hdr);
432	} else {	646	} else {
433	$cb->($_[0], $_[1]);	647	# body handling, four different code paths
		648	# for want_body_handle, on_body (2x), normal (2x)
		649	# we might read too much here, but it does not matter yet (no pers. connections)
		650	if (!$redirect && $arg{want_body_handle}) {
		651	$_[0]->on_eof (undef);
		652	$_[0]->on_error (undef);
		653	$_[0]->on_read (undef);
		654
		655	$finish->(delete $state{handle}, \%hdr);
		656
		657	} elsif ($arg{on_body}) {
		658	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		659	if ($len) {
		660	$_[0]->on_eof (undef);
		661	$_[0]->on_read (sub {
		662	$len -= length $_[0]{rbuf};
		663
		664	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		665	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		666
		667	$len > 0
		668	or $finish->("", \%hdr);
		669	});
		670	} else {
		671	$_[0]->on_eof (sub {
		672	$finish->("", \%hdr);
		673	});
		674	$_[0]->on_read (sub {
		675	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		676	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
		677	});
		678	}
		679	} else {
		680	$_[0]->on_eof (undef);
		681
		682	if ($len) {
		683	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
		684	$_[0]->on_read (sub {
		685	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		686	if $len <= length $_[0]{rbuf};
		687	});
		688	} else {
		689	$_[0]->on_error (sub {
		690	$! == Errno::EPIPE \|\| !$!
		691	? $finish->(delete $_[0]{rbuf}, \%hdr)
		692	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });
		693	});
		694	$_[0]->on_read (sub { });
		695	}
		696	}
434	}	697	}
435	};	698	});
		699	});
		700	};
436		701
437	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	702	# now handle proxy-CONNECT method
438	$finish->(undef, \%hdr);	703	if ($proxy && $uscheme eq "https") {
		704	# oh dear, we have to wrap it into a connect request
		705
		706	# maybe re-use $uauthority with patched port?
		707	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		708	$state{handle}->push_read (line => $qr_nlnl, sub {
		709	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		710	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));
		711
		712	if ($2 == 200) {
		713	$rpath = $upath;
		714	&$handle_actual_request;
439	} else {	715	} else {
440	if (exists $hdr{"content-length"}) {	716	%state = ();
441	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {	717	$cb->(undef, { Status => $2, Reason => $3, URL => $url });
442	# could cache persistent connection now
443	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
444	# but we don't, due to misdesigns, this is annoyingly complex
445	};
446
447	$finish->($_[1], \%hdr);
448	});
449	} else {
450	# too bad, need to read until we get an error or EOF,
451	# no way to detect winged data.
452	$_[0]->on_error (sub {
453	$finish->($_[0]{rbuf}, \%hdr);
454	});
455	$_[0]->on_eof (undef);
456	$_[0]->on_read (sub { });
457	}
458	}	718	}
459	});	719	});
		720	} else {
		721	&$handle_actual_request;
460	});	722	}
461	}, sub {	723
462	$timeout	724	}, $arg{on_prepare} \|\| sub { $timeout };
463	};
464	};	725	};
465		726
466	defined wantarray && AnyEvent::Util::guard { %state = () }	727	defined wantarray && AnyEvent::Util::guard { %state = () }
467	}	728	}
468		729
…		…
489	=over 4	750	=over 4
490		751
491	=item AnyEvent::HTTP::set_proxy "proxy-url"	752	=item AnyEvent::HTTP::set_proxy "proxy-url"
492		753
493	Sets the default proxy server to use. The proxy-url must begin with a	754	Sets the default proxy server to use. The proxy-url must begin with a
494	string of the form C<http://host:port> (optionally C<https:...>).	755	string of the form C<http://host:port> (optionally C<https:...>), croaks
		756	otherwise.
		757
		758	To clear an already-set proxy, use C<undef>.
495		759
496	=item $AnyEvent::HTTP::MAX_RECURSE	760	=item $AnyEvent::HTTP::MAX_RECURSE
497		761
498	The default value for the C<recurse> request parameter (default: C<10>).	762	The default value for the C<recurse> request parameter (default: C<10>).
499		763
500	=item $AnyEvent::HTTP::USERAGENT	764	=item $AnyEvent::HTTP::USERAGENT
501		765
502	The default value for the C<User-Agent> header (the default is	766	The default value for the C<User-Agent> header (the default is
503	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	767	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
504		768
505	=item $AnyEvent::HTTP::MAX_PERSISTENT	769	=item $AnyEvent::HTTP::MAX_PER_HOST
506		770
507	The maximum number of persistent connections to keep open (default: 8).	771	The maximum number of concurrent connections to the same host (identified
		772	by the hostname). If the limit is exceeded, then the additional requests
		773	are queued until previous connections are closed.
508		774
509	Not implemented currently.	775	The default value for this is C<4>, and it is highly advisable to not
510		776	increase it.
511	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
512
513	The maximum time to cache a persistent connection, in seconds (default: 2).
514
515	Not implemented currently.
516		777
517	=item $AnyEvent::HTTP::ACTIVE	778	=item $AnyEvent::HTTP::ACTIVE
518		779
519	The number of active connections. This is not the number of currently	780	The number of active connections. This is not the number of currently
520	running requests, but the number of currently open and non-idle TCP	781	running requests, but the number of currently open and non-idle TCP
…		…
523	=back	784	=back
524		785
525	=cut	786	=cut
526		787
527	sub set_proxy($) {	788	sub set_proxy($) {
		789	if (length $_[0]) {
528	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	790	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		791	or Carp::croak "$_[0]: invalid proxy URL";
		792	$PROXY = [$2, $3 \|\| 3128, $1]
		793	} else {
		794	undef $PROXY;
		795	}
529	}	796	}
530		797
531	# initialise proxy from environment	798	# initialise proxy from environment
		799	eval {
532	set_proxy $ENV{http_proxy};	800	set_proxy $ENV{http_proxy};
		801	};
533		802
534	=head1 SEE ALSO	803	=head1 SEE ALSO
535		804
536	L<AnyEvent>.	805	L<AnyEvent>.
537		806
538	=head1 AUTHOR	807	=head1 AUTHOR
539		808
540	Marc Lehmann <schmorp@schmorp.de>	809	Marc Lehmann <schmorp@schmorp.de>
541	http://home.schmorp.de/	810	http://home.schmorp.de/
542		811
		812	With many thanks to Дмитрий Шалашов, who provided countless
		813	testcases and bugreports.
		814
543	=cut	815	=cut
544		816
545	1	817	1
546		818

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.24 by root, Wed Jul 2 01:30:33 2008 UTC vs. Revision 1.54 by root, Wed Jun 16 18:09:52 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.24 by root, Wed Jul 2 01:30:33 2008 UTC vs.
Revision 1.54 by root, Wed Jun 16 18:09:52 2010 UTC