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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.29 by root, Wed Oct 22 23:28:11 2008 UTC vs.
Revision 1.60 by root, Thu Dec 30 02:56:28 2010 UTC

…		…
39	package AnyEvent::HTTP;	39	package AnyEvent::HTTP;
40		40
41	use strict;	41	use strict;
42	no warnings;	42	no warnings;
43		43
44	use Carp;	44	use Errno ();
45		45
46	use AnyEvent ();	46	use AnyEvent 5.0 ();
47	use AnyEvent::Util ();	47	use AnyEvent::Util ();
48	use AnyEvent::Socket ();
49	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
50		49
51	use base Exporter::;	50	use base Exporter::;
52		51
53	our $VERSION = '1.05';	52	our $VERSION = '1.46';
54		53
55	our @EXPORT = qw(http_get http_post http_head http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
56		55
57	our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";	56	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
59	our $MAX_PERSISTENT = 8;	58	our $MAX_PERSISTENT = 8;
60	our $PERSISTENT_TIMEOUT = 2;	59	our $PERSISTENT_TIMEOUT = 2;
61	our $TIMEOUT = 300;	60	our $TIMEOUT = 300;
62		61
63	# changing these is evil	62	# changing these is evil
64	our $MAX_PERSISTENT_PER_HOST = 2;	63	our $MAX_PERSISTENT_PER_HOST = 0;
65	our $MAX_PER_HOST = 4;	64	our $MAX_PER_HOST = 4;
66		65
67	our $PROXY;	66	our $PROXY;
68	our $ACTIVE = 0;	67	our $ACTIVE = 0;
69		68
…		…
92	must be an absolute http or https URL.	91	must be an absolute http or https URL.
93		92
94	When called in void context, nothing is returned. In other contexts,	93	When called in void context, nothing is returned. In other contexts,
95	C<http_request> returns a "cancellation guard" - you have to keep the	94	C<http_request> returns a "cancellation guard" - you have to keep the
96	object at least alive until the callback get called. If the object gets	95	object at least alive until the callback get called. If the object gets
97	destroyed before the callbakc is called, the request will be cancelled.	96	destroyed before the callback is called, the request will be cancelled.
98		97
99	The callback will be called with the response data as first argument	98	The callback will be called with the response body data as first argument
100	(or C<undef> if it wasn't available due to errors), and a hash-ref with	99	(or C<undef> if an error occured), and a hash-ref with response headers as
101	response headers as second argument.	100	second argument.
102		101
103	All the headers in that hash are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
105	contain the three parts of the HTTP Status-Line of the same name. The	105	three parts of the HTTP Status-Line of the same name.
		106
106	pseudo-header C<URL> contains the original URL (which can differ from the	107	The pseudo-header C<URL> contains the actual URL (which can differ from
107	requested URL when following redirects).	108	the requested URL when following redirects - for example, you might get
		109	an error that your URL scheme is not supported even though your URL is a
		110	valid http URL because it redirected to an ftp URL, in which case you can
		111	look at the URL pseudo header).
108		112
		113	The pseudo-header C<Redirect> only exists when the request was a result
		114	of an internal redirect. In that case it is an array reference with
		115	the C<($data, $headers)> from the redirect response. Note that this
		116	response could in turn be the result of a redirect itself, and C<<
		117	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		118	response, and so on.
		119
109	If the server sends a header multiple lines, then their contents will be	120	If the server sends a header multiple times, then their contents will be
110	joined together with C<\x00>.	121	joined together with a comma (C<,>), as per the HTTP spec.
111		122
112	If an internal error occurs, such as not being able to resolve a hostname,	123	If an internal error occurs, such as not being able to resolve a hostname,
113	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>	124	then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<59x>
114	and the C<Reason> pseudo-header will contain an error message.	125	(usually C<599>) and the C<Reason> pseudo-header will contain an error
		126	message.
115		127
116	A typical callback might look like this:	128	A typical callback might look like this:
117		129
118	sub {	130	sub {
119	my ($body, $hdr) = @_;	131	my ($body, $hdr) = @_;
…		…
137		149
138	=item headers => hashref	150	=item headers => hashref
139		151
140	The request headers to use. Currently, C<http_request> may provide its	152	The request headers to use. Currently, C<http_request> may provide its
141	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	153	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
142	and will provide defaults for C<User-Agent:> and C<Referer:>.	154	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		155	suppressed by using C<undef> for these headers in which case they won't be
		156	sent at all).
143		157
144	=item timeout => $seconds	158	=item timeout => $seconds
145		159
146	The time-out to use for various stages - each connect attempt will reset	160	The time-out to use for various stages - each connect attempt will reset
147	the timeout, as will read or write activity. Default timeout is 5 minutes.	161	the timeout, as will read or write activity, i.e. this is not an overall
		162	timeout.
		163
		164	Default timeout is 5 minutes.
148		165
149	=item proxy => [$host, $port[, $scheme]] or undef	166	=item proxy => [$host, $port[, $scheme]] or undef
150		167
151	Use the given http proxy for all requests. If not specified, then the	168	Use the given http proxy for all requests. If not specified, then the
152	default proxy (as specified by C<$ENV{http_proxy}>) is used.	169	default proxy (as specified by C<$ENV{http_proxy}>) is used.
153		170
154	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	171	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
155	HTTPS.	172	HTTPS.
156		173
157	=item body => $string	174	=item body => $string
158		175
159	The request body, usually empty. Will be-sent as-is (future versions of	176	The request body, usually empty. Will be-sent as-is (future versions of
…		…
165	based on the original netscape specification.	182	based on the original netscape specification.
166		183
167	The C<$hash_ref> must be an (initially empty) hash reference which will	184	The C<$hash_ref> must be an (initially empty) hash reference which will
168	get updated automatically. It is possible to save the cookie_jar to	185	get updated automatically. It is possible to save the cookie_jar to
169	persistent storage with something like JSON or Storable, but this is not	186	persistent storage with something like JSON or Storable, but this is not
170	recommended, as expire times are currently being ignored.	187	recommended, as expiry times are currently being ignored.
171		188
172	Note that this cookie implementation is not of very high quality, nor	189	Note that this cookie implementation is not of very high quality, nor
173	meant to be complete. If you want complete cookie management you have to	190	meant to be complete. If you want complete cookie management you have to
174	do that on your own. C<cookie_jar> is meant as a quick fix to get some	191	do that on your own. C<cookie_jar> is meant as a quick fix to get some
175	cookie-using sites working. Cookies are a privacy disaster, do not use	192	cookie-using sites working. Cookies are a privacy disaster, do not use
176	them unless required to.	193	them unless required to.
		194
		195	=item tls_ctx => $scheme \| $tls_ctx
		196
		197	Specifies the AnyEvent::TLS context to be used for https connections. This
		198	parameter follows the same rules as the C<tls_ctx> parameter to
		199	L<AnyEvent::Handle>, but additionally, the two strings C<low> or
		200	C<high> can be specified, which give you a predefined low-security (no
		201	verification, highest compatibility) and high-security (CA and common-name
		202	verification) TLS context.
		203
		204	The default for this option is C<low>, which could be interpreted as "give
		205	me the page, no matter what".
		206
		207	=item on_prepare => $callback->($fh)
		208
		209	In rare cases you need to "tune" the socket before it is used to
		210	connect (for exmaple, to bind it on a given IP address). This parameter
		211	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		212	and behaves exactly the same way (e.g. it has to provide a
		213	timeout). See the description for the C<$prepare_cb> argument of
		214	C<AnyEvent::Socket::tcp_connect> for details.
		215
		216	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		217
		218	In even rarer cases you want total control over how AnyEvent::HTTP
		219	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		220	to do this, but you can provide your own C<tcp_connect> function -
		221	obviously, it has to follow the same calling conventions, except that it
		222	may always return a connection guard object.
		223
		224	There are probably lots of weird uses for this function, starting from
		225	tracing the hosts C<http_request> actually tries to connect, to (inexact
		226	but fast) host => IP address caching or even socks protocol support.
		227
		228	=item on_header => $callback->($headers)
		229
		230	When specified, this callback will be called with the header hash as soon
		231	as headers have been successfully received from the remote server (not on
		232	locally-generated errors).
		233
		234	It has to return either true (in which case AnyEvent::HTTP will continue),
		235	or false, in which case AnyEvent::HTTP will cancel the download (and call
		236	the finish callback with an error code of C<598>).
		237
		238	This callback is useful, among other things, to quickly reject unwanted
		239	content, which, if it is supposed to be rare, can be faster than first
		240	doing a C<HEAD> request.
		241
		242	Example: cancel the request unless the content-type is "text/html".
		243
		244	on_header => sub {
		245	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
		246	},
		247
		248	=item on_body => $callback->($partial_body, $headers)
		249
		250	When specified, all body data will be passed to this callback instead of
		251	to the completion callback. The completion callback will get the empty
		252	string instead of the body data.
		253
		254	It has to return either true (in which case AnyEvent::HTTP will continue),
		255	or false, in which case AnyEvent::HTTP will cancel the download (and call
		256	the completion callback with an error code of C<598>).
		257
		258	This callback is useful when the data is too large to be held in memory
		259	(so the callback writes it to a file) or when only some information should
		260	be extracted, or when the body should be processed incrementally.
		261
		262	It is usually preferred over doing your own body handling via
		263	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		264	only used to create a connection, C<want_body_handle> is the better
		265	alternative, as it allows you to install your own event handler, reducing
		266	resource usage.
		267
		268	=item want_body_handle => $enable
		269
		270	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
		271	changes considerably: after parsing the headers, and instead of
		272	downloading the body (if any), the completion callback will be
		273	called. Instead of the C<$body> argument containing the body data, the
		274	callback will receive the L<AnyEvent::Handle> object associated with the
		275	connection. In error cases, C<undef> will be passed. When there is no body
		276	(e.g. status C<304>), the empty string will be passed.
		277
		278	The handle object might or might not be in TLS mode, might be connected to
		279	a proxy, be a persistent connection etc., and configured in unspecified
		280	ways. The user is responsible for this handle (it will not be used by this
		281	module anymore).
		282
		283	This is useful with some push-type services, where, after the initial
		284	headers, an interactive protocol is used (typical example would be the
		285	push-style twitter API which starts a JSON/XML stream).
		286
		287	If you think you need this, first have a look at C<on_body>, to see if
		288	that doesn't solve your problem in a better way.
177		289
178	=back	290	=back
179		291
180	Example: make a simple HTTP GET request for http://www.nethype.de/	292	Example: make a simple HTTP GET request for http://www.nethype.de/
181		293
…		…
237	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	349	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
238		350
239	_slot_schedule $_[0];	351	_slot_schedule $_[0];
240	}	352	}
241		353
		354	our $qr_nlnl = qr{(?<![^\012])\015?\012};
		355
		356	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
		357	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
		358
242	sub http_request($$@) {	359	sub http_request($$@) {
243	my $cb = pop;	360	my $cb = pop;
244	my ($method, $url, %arg) = @_;	361	my ($method, $url, %arg) = @_;
245		362
246	my %hdr;	363	my %hdr;
		364
		365	$arg{tls_ctx} = $TLS_CTX_LOW if $arg{tls_ctx} eq "low" \|\| !exists $arg{tls_ctx};
		366	$arg{tls_ctx} = $TLS_CTX_HIGH if $arg{tls_ctx} eq "high";
247		367
248	$method = uc $method;	368	$method = uc $method;
249		369
250	if (my $hdr = $arg{headers}) {	370	if (my $hdr = $arg{headers}) {
251	while (my ($k, $v) = each %$hdr) {	371	while (my ($k, $v) = each %$hdr) {
252	$hdr{lc $k} = $v;	372	$hdr{lc $k} = $v;
253	}	373	}
254	}	374	}
255		375
		376	# pseudo headers for all subsequent responses
		377	my @pseudo = (URL => $url);
		378	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		379
256	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	380	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
257		381
258	return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })	382	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })
259	if $recurse < 0;	383	if $recurse < 0;
260		384
261	my $proxy = $arg{proxy} \|\| $PROXY;	385	my $proxy = $arg{proxy} \|\| $PROXY;
262	my $timeout = $arg{timeout} \|\| $TIMEOUT;	386	my $timeout = $arg{timeout} \|\| $TIMEOUT;
263		387
264	$hdr{"user-agent"} \|\|= $USERAGENT;
265
266	my ($scheme, $authority, $upath, $query, $fragment) =	388	my ($uscheme, $uauthority, $upath, $query, $fragment) =
267	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	389	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
268		390
269	$scheme = lc $scheme;	391	$uscheme = lc $uscheme;
270		392
271	my $uport = $scheme eq "http" ? 80	393	my $uport = $uscheme eq "http" ? 80
272	: $scheme eq "https" ? 443	394	: $uscheme eq "https" ? 443
273	: return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });	395	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });
274		396
275	$hdr{referer} \|\|= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
276
277	$authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	397	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
278	or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });	398	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });
279		399
280	my $uhost = $1;	400	my $uhost = $1;
281	$uport = $2 if defined $2;	401	$uport = $2 if defined $2;
282		402
		403	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		404	unless exists $hdr{host};
		405
283	$uhost =~ s/^\[(.*)\]$/$1/;	406	$uhost =~ s/^\[(.*)\]$/$1/;
284	$upath .= "?$query" if length $query;	407	$upath .= $query if length $query;
285		408
286	$upath =~ s%^/?%/%;	409	$upath =~ s%^/?%/%;
287		410
288	# cookie processing	411	# cookie processing
289	if (my $jar = $arg{cookie_jar}) {	412	if (my $jar = $arg{cookie_jar}) {
290	%$jar = () if $jar->{version} < 1;	413	%$jar = () if $jar->{version} != 1;
291		414
292	my @cookie;	415	my @cookie;
293		416
294	while (my ($chost, $v) = each %$jar) {	417	while (my ($chost, $v) = each %$jar) {
		418	if ($chost =~ /^\./) {
295	next unless $chost eq substr $uhost, -length $chost;	419	next unless $chost eq substr $uhost, -length $chost;
296	next unless $chost =~ /^\./;	420	} elsif ($chost =~ /\./) {
		421	next unless $chost eq $uhost;
		422	} else {
		423	next;
		424	}
297		425
298	while (my ($cpath, $v) = each %$v) {	426	while (my ($cpath, $v) = each %$v) {
299	next unless $cpath eq substr $upath, 0, length $cpath;	427	next unless $cpath eq substr $upath, 0, length $cpath;
300		428
301	while (my ($k, $v) = each %$v) {	429	while (my ($k, $v) = each %$v) {
302	next if $scheme ne "https" && exists $v->{secure};	430	next if $uscheme ne "https" && exists $v->{secure};
		431	my $value = $v->{value};
		432	$value =~ s/([\\"])/\\$1/g;
303	push @cookie, "$k=$v->{value}";	433	push @cookie, "$k=\"$value\"";
304	}	434	}
305	}	435	}
306	}	436	}
307		437
308	$hdr{cookie} = join "; ", @cookie	438	$hdr{cookie} = join "; ", @cookie
309	if @cookie;	439	if @cookie;
310	}	440	}
311		441
312	my ($rhost, $rport, $rpath); # request host, port, path	442	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
313		443
314	if ($proxy) {	444	if ($proxy) {
315	($rhost, $rport, $scheme) = @$proxy;	445	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
316	$rpath = $url;	446
		447	$rscheme = "http" unless defined $rscheme;
		448
		449	# don't support https requests over https-proxy transport,
		450	# can't be done with tls as spec'ed, unless you double-encrypt.
		451	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
317	} else {	452	} else {
318	($rhost, $rport, $rpath) = ($uhost, $uport, $upath);	453	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
319	$hdr{host} = $uhost;
320	}	454	}
321		455
		456	# leave out fragment and query string, just a heuristic
		457	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		458	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};
		459
322	$hdr{"content-length"} = length $arg{body};	460	$hdr{"content-length"} = length $arg{body}
		461	if length $arg{body} \|\| $method ne "GET";
323		462
324	my %state = (connect_guard => 1);	463	my %state = (connect_guard => 1);
325		464
326	_get_slot $uhost, sub {	465	_get_slot $uhost, sub {
327	$state{slot_guard} = shift;	466	$state{slot_guard} = shift;
328		467
329	return unless $state{connect_guard};	468	return unless $state{connect_guard};
330		469
331	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	470	my $tcp_connect = $arg{tcp_connect}
		471	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		472
		473	$state{connect_guard} = $tcp_connect->(
		474	$rhost,
		475	$rport,
		476	sub {
332	$state{fh} = shift	477	$state{fh} = shift
333	or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });	478	or do {
334
335	delete $state{connect_guard}; # reduce memory usage, save a tree
336
337	# get handle
338	$state{handle} = new AnyEvent::Handle
339	fh => $state{fh},
340	($scheme eq "https" ? (tls => "connect") : ());
341
342	# limit the number of persistent connections
343	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
344	++$KA_COUNT{$_[1]};
345	$state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
346	$hdr{connection} = "keep-alive";
347	delete $hdr{connection}; # keep-alive not yet supported
348	} else {
349	delete $hdr{connection};
350	}
351
352	# (re-)configure handle
353	$state{handle}->timeout ($timeout);
354	$state{handle}->on_error (sub {
355	my $errno = "$!";	479	my $err = "$!";
356	%state = ();
357	$cb->(undef, { Status => 599, Reason => $errno, URL => $url });
358	});
359	$state{handle}->on_eof (sub {
360	%state = ();
361	$cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
362	});
363
364	# send request
365	$state{handle}->push_write (
366	"$method $rpath HTTP/1.0\015\012"
367	. (join "", map "$_: $hdr{$_}\015\012", keys %hdr)
368	. "\015\012"
369	. (delete $arg{body})
370	);
371
372	%hdr = (); # reduce memory usage, save a kitten
373
374	# status line
375	$state{handle}->push_read (line => qr/\015?\012/, sub {
376	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
377	or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
378
379	my %hdr = ( # response headers
380	HTTPVersion => "\x00$1",
381	Status => "\x00$2",
382	Reason => "\x00$3",
383	URL => "\x00$url"
384	);
385
386	# headers, could be optimized a bit
387	$state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
388	for ("$_[1]\012") {
389	# we support spaces in field names, as lotus domino
390	# creates them.
391	$hdr{lc $1} .= "\x00$2"
392	while /\G
393	([^:\000-\037]+):
394	[\011\040]*
395	((?: [^\015\012]+ \| \015?\012[\011\040] )*)
396	\015?\012
397	/gxc;
398
399	/\G$/
400	or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));
401	}
402
403	substr $_, 0, 1, ""
404	for values %hdr;
405
406	my $finish = sub {
407	%state = ();	480	%state = ();
		481	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });
		482	};
408		483
409	# set-cookie processing	484	pop; # free memory, save a tree
410	if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {
411	for (split /\x00/, $hdr{"set-cookie"}) {
412	my ($cookie, @arg) = split /;\s*/;
413	my ($name, $value) = split /=/, $cookie, 2;
414	my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
415
416	my $cdom = (delete $kv{domain}) \|\| $uhost;
417	my $cpath = (delete $kv{path}) \|\| "/";
418
419	$cdom =~ s/^\.?/./; # make sure it starts with a "."
420		485
421	next if $cdom =~ /\.$/;	486	return unless delete $state{connect_guard};
422		487
423	# this is not rfc-like and not netscape-like. go figure.	488	# get handle
424	my $ndots = $cdom =~ y/.//;	489	$state{handle} = new AnyEvent::Handle
425	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);	490	fh => $state{fh},
426		491	peername => $rhost,
427	# store it	492	tls_ctx => $arg{tls_ctx},
428	$arg{cookie_jar}{version} = 1;	493	# these need to be reconfigured on keepalive handles
429	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;	494	timeout => $timeout,
		495	on_error => sub {
		496	%state = ();
		497	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });
		498	},
		499	on_eof => sub {
		500	%state = ();
		501	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });
		502	},
		503	;
		504
		505	# limit the number of persistent connections
		506	# keepalive not yet supported
		507	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
		508	# ++$KA_COUNT{$_[1]};
		509	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
		510	# --$KA_COUNT{$_[1]}
		511	# };
		512	# $hdr{connection} = "keep-alive";
		513	# } else {
		514	delete $hdr{connection};
		515	# }
		516
		517	$state{handle}->starttls ("connect") if $rscheme eq "https";
		518
		519	# handle actual, non-tunneled, request
		520	my $handle_actual_request = sub {
		521	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
		522
		523	# send request
		524	$state{handle}->push_write (
		525	"$method $rpath HTTP/1.0\015\012"
		526	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
		527	. "\015\012"
		528	. (delete $arg{body})
		529	);
		530
		531	# return if error occured during push_write()
		532	return unless %state;
		533
		534	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
		535
		536	# status line and headers
		537	$state{handle}->push_read (line => $qr_nlnl, sub {
		538	for ("$_[1]") {
		539	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		540
		541	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc
		542	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));
		543
		544	push @pseudo,
		545	HTTPVersion => $1,
		546	Status => $2,
		547	Reason => $3,
430	}	548	;
		549
		550	# things seen, not parsed:
		551	# p3pP="NON CUR OTPi OUR NOR UNI"
		552
		553	$hdr{lc $1} .= ",$2"
		554	while /\G
		555	([^:\000-\037]*):
		556	[\011\040]*
		557	((?: [^\012]+ \| \012[\011\040] )*)
		558	\012
		559	/gxc;
		560
		561	/\G$/
		562	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));
431	}	563	}
432		564
		565	# remove the "," prefix we added to all headers above
		566	substr $_, 0, 1, ""
		567	for values %hdr;
		568
		569	# patch in all pseudo headers
		570	%hdr = (%hdr, @pseudo);
		571
		572	# redirect handling
433	# microsoft and other shitheads don't give a shit for following standards,	573	# microsoft and other shitheads don't give a shit for following standards,
434	# try to support some common forms of broken Location headers.	574	# try to support some common forms of broken Location headers.
435	if ($_[1]{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {	575	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
436	$_[1]{location} =~ s/^\.\/+//;	576	$hdr{location} =~ s/^\.\/+//;
437		577
438	my $url = "$scheme://$uhost:$uport";	578	my $url = "$rscheme://$uhost:$uport";
439		579
440	unless ($_[1]{location} =~ s/^\///) {	580	unless ($hdr{location} =~ s/^\///) {
441	$url .= $upath;	581	$url .= $upath;
442	$url =~ s/\/[^\/]*$//;	582	$url =~ s/\/[^\/]*$//;
443	}	583	}
444		584
445	$_[1]{location} = "$url/$_[1]{location}";	585	$hdr{location} = "$url/$hdr{location}";
446	}	586	}
447		587
448	if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {	588	my $redirect;
449	# apparently, mozilla et al. just change POST to GET here	589
450	# more research is needed before we do the same	590	if ($recurse) {
451	http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	591	my $status = $hdr{Status};
452	} elsif ($_[1]{Status} == 303 && $recurse) {	592
		593	# industry standard is to redirect POST as GET for
		594	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		595	# also, the UA should ask the user for 301 and 307 and POST,
		596	# industry standard seems to be to simply follow.
		597	# we go with the industry standard.
		598	if ($status == 301 or $status == 302 or $status == 303) {
453	# even http/1.1 is unlear on how to mutate the method	599	# HTTP/1.1 is unclear on how to mutate the method
454	$method = "GET" unless $method eq "HEAD";	600	$method = "GET" unless $method eq "HEAD";
455	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	601	$redirect = 1;
456	} elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET\|HEAD)$/) {	602	} elsif ($status == 307) {
457	http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);	603	$redirect = 1;
		604	}
		605	}
		606
		607	my $finish = sub {
		608	$state{handle}->destroy if $state{handle};
		609	%state = ();
		610
		611	# set-cookie processing
		612	if ($arg{cookie_jar}) {
		613	for ($_[1]{"set-cookie"}) {
		614	# parse NAME=VALUE
		615	my @kv;
		616
		617	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
		618	my $name = $1;
		619	my $value = $3;
		620
		621	unless ($value) {
		622	$value = $2;
		623	$value =~ s/\\(.)/$1/gs;
		624	}
		625
		626	push @kv, $name => $value;
		627
		628	last unless /\G\s*;/gc;
		629	}
		630
		631	last unless @kv;
		632
		633	my $name = shift @kv;
		634	my %kv = (value => shift @kv, @kv);
		635
		636	my $cdom;
		637	my $cpath = (delete $kv{path}) \|\| "/";
		638
		639	if (exists $kv{domain}) {
		640	$cdom = delete $kv{domain};
		641
		642	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		643
		644	next if $cdom =~ /\.$/;
		645
		646	# this is not rfc-like and not netscape-like. go figure.
		647	my $ndots = $cdom =~ y/.//;
		648	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		649	} else {
		650	$cdom = $uhost;
		651	}
		652
		653	# store it
		654	$arg{cookie_jar}{version} = 1;
		655	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		656
		657	redo if /\G\s*,/gc;
		658	}
		659	}
		660
		661	if ($redirect && exists $hdr{location}) {
		662	# we ignore any errors, as it is very common to receive
		663	# Content-Length != 0 but no actual body
		664	# we also access %hdr, as $_[1] might be an erro
		665	http_request (
		666	$method => $hdr{location},
		667	%arg,
		668	recurse => $recurse - 1,
		669	Redirect => \@_,
		670	$cb);
		671	} else {
		672	$cb->($_[0], $_[1]);
		673	}
		674	};
		675
		676	my $len = $hdr{"content-length"};
		677
		678	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		679	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
		680	} elsif (
		681	$hdr{Status} =~ /^(?:1..\|[23]04)$/
		682	or $method eq "HEAD"
		683	or (defined $len && !$len)
		684	) {
		685	# no body
		686	$finish->("", \%hdr);
458	} else {	687	} else {
459	$cb->($_[0], $_[1]);	688	# body handling, four different code paths
		689	# for want_body_handle, on_body (2x), normal (2x)
		690	# we might read too much here, but it does not matter yet (no pers. connections)
		691	if (!$redirect && $arg{want_body_handle}) {
		692	$_[0]->on_eof (undef);
		693	$_[0]->on_error (undef);
		694	$_[0]->on_read (undef);
		695
		696	$finish->(delete $state{handle}, \%hdr);
		697
		698	} elsif ($arg{on_body}) {
		699	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		700	if ($len) {
		701	$_[0]->on_eof (undef);
		702	$_[0]->on_read (sub {
		703	$len -= length $_[0]{rbuf};
		704
		705	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		706	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		707
		708	$len > 0
		709	or $finish->("", \%hdr);
		710	});
		711	} else {
		712	$_[0]->on_eof (sub {
		713	$finish->("", \%hdr);
		714	});
		715	$_[0]->on_read (sub {
		716	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		717	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
		718	});
		719	}
		720	} else {
		721	$_[0]->on_eof (undef);
		722
		723	if ($len) {
		724	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
		725	$_[0]->on_read (sub {
		726	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)
		727	if $len <= length $_[0]{rbuf};
		728	});
		729	} else {
		730	$_[0]->on_error (sub {
		731	($! == Errno::EPIPE \|\| !$!)
		732	? $finish->(delete $_[0]{rbuf}, \%hdr)
		733	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });
		734	});
		735	$_[0]->on_read (sub { });
		736	}
		737	}
460	}	738	}
461	};	739	});
		740	};
462		741
463	if ($hdr{Status} =~ /^(?:1..\|204\|304)$/ or $method eq "HEAD") {	742	# now handle proxy-CONNECT method
464	$finish->(undef, \%hdr);	743	if ($proxy && $uscheme eq "https") {
465	} else {	744	# oh dear, we have to wrap it into a connect request
466	if (exists $hdr{"content-length"}) {
467	$_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
468	# could cache persistent connection now
469	if ($hdr{connection} =~ /\bkeep-alive\b/i) {
470	# but we don't, due to misdesigns, this is annoyingly complex
471	};
472		745
473	$finish->($_[1], \%hdr);	746	# maybe re-use $uauthority with patched port?
474	});	747	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
		748	$state{handle}->push_read (line => $qr_nlnl, sub {
		749	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
		750	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));
		751
		752	if ($2 == 200) {
		753	$rpath = $upath;
		754	&$handle_actual_request;
475	} else {	755	} else {
476	# too bad, need to read until we get an error or EOF,
477	# no way to detect winged data.
478	$_[0]->on_error (sub {
479	$finish->($_[0]{rbuf}, \%hdr);
480	});	756	%state = ();
481	$_[0]->on_eof (undef);	757	$cb->(undef, { Status => $2, Reason => $3, @pseudo });
482	$_[0]->on_read (sub { });
483	}	758	}
484	}	759	});
		760	} else {
		761	&$handle_actual_request;
485	});	762	}
		763
486	});	764	},
487	}, sub {	765	$arg{on_prepare} \|\| sub { $timeout }
488	$timeout
489	};	766	);
490	};	767	};
491		768
492	defined wantarray && AnyEvent::Util::guard { %state = () }	769	defined wantarray && AnyEvent::Util::guard { %state = () }
493	}	770	}
494		771
…		…
508	&http_request	785	&http_request
509	}	786	}
510		787
511	=back	788	=back
512		789
		790	=head2 DNS CACHING
		791
		792	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		793	the actual connection, which in turn uses AnyEvent::DNS to resolve
		794	hostnames. The latter is a simple stub resolver and does no caching
		795	on its own. If you want DNS caching, you currently have to provide
		796	your own default resolver (by storing a suitable resolver object in
		797	C<$AnyEvent::DNS::RESOLVER>).
		798
513	=head2 GLOBAL FUNCTIONS AND VARIABLES	799	=head2 GLOBAL FUNCTIONS AND VARIABLES
514		800
515	=over 4	801	=over 4
516		802
517	=item AnyEvent::HTTP::set_proxy "proxy-url"	803	=item AnyEvent::HTTP::set_proxy "proxy-url"
518		804
519	Sets the default proxy server to use. The proxy-url must begin with a	805	Sets the default proxy server to use. The proxy-url must begin with a
520	string of the form C<http://host:port> (optionally C<https:...>).	806	string of the form C<http://host:port> (optionally C<https:...>), croaks
		807	otherwise.
		808
		809	To clear an already-set proxy, use C<undef>.
521		810
522	=item $AnyEvent::HTTP::MAX_RECURSE	811	=item $AnyEvent::HTTP::MAX_RECURSE
523		812
524	The default value for the C<recurse> request parameter (default: C<10>).	813	The default value for the C<recurse> request parameter (default: C<10>).
525		814
526	=item $AnyEvent::HTTP::USERAGENT	815	=item $AnyEvent::HTTP::USERAGENT
527		816
528	The default value for the C<User-Agent> header (the default is	817	The default value for the C<User-Agent> header (the default is
529	C<Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	818	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
530		819
531	=item $AnyEvent::HTTP::MAX_PERSISTENT	820	=item $AnyEvent::HTTP::MAX_PER_HOST
532		821
533	The maximum number of persistent connections to keep open (default: 8).	822	The maximum number of concurrent connections to the same host (identified
		823	by the hostname). If the limit is exceeded, then the additional requests
		824	are queued until previous connections are closed.
534		825
535	Not implemented currently.	826	The default value for this is C<4>, and it is highly advisable to not
536		827	increase it.
537	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
538
539	The maximum time to cache a persistent connection, in seconds (default: 2).
540
541	Not implemented currently.
542		828
543	=item $AnyEvent::HTTP::ACTIVE	829	=item $AnyEvent::HTTP::ACTIVE
544		830
545	The number of active connections. This is not the number of currently	831	The number of active connections. This is not the number of currently
546	running requests, but the number of currently open and non-idle TCP	832	running requests, but the number of currently open and non-idle TCP
…		…
549	=back	835	=back
550		836
551	=cut	837	=cut
552		838
553	sub set_proxy($) {	839	sub set_proxy($) {
		840	if (length $_[0]) {
554	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	841	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		842	or Carp::croak "$_[0]: invalid proxy URL";
		843	$PROXY = [$2, $3 \|\| 3128, $1]
		844	} else {
		845	undef $PROXY;
		846	}
555	}	847	}
556		848
557	# initialise proxy from environment	849	# initialise proxy from environment
		850	eval {
558	set_proxy $ENV{http_proxy};	851	set_proxy $ENV{http_proxy};
		852	};
		853
		854	=head2 SOCKS PROXIES
		855
		856	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		857	compile your perl to support socks, or use an external program such as
		858	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		859	transparently.
		860
		861	Alternatively, for AnyEvent::HTTP only, you can use your own
		862	C<tcp_connect> function that does the proxy handshake - here is an example
		863	that works with socks4a proxies:
		864
		865	use Errno;
		866	use AnyEvent::Util;
		867	use AnyEvent::Socket;
		868	use AnyEvent::Handle;
		869
		870	# host, port and username of/for your socks4a proxy
		871	my $socks_host = "10.0.0.23";
		872	my $socks_port = 9050;
		873	my $socks_user = "";
		874
		875	sub socks4a_connect {
		876	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		877
		878	my $hdl = new AnyEvent::Handle
		879	connect => [$socks_host, $socks_port],
		880	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		881	on_error => sub { $connect_cb->() },
		882	;
		883
		884	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		885
		886	$hdl->push_read (chunk => 8, sub {
		887	my ($hdl, $chunk) = @_;
		888	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		889
		890	if ($status == 0x5a) {
		891	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		892	} else {
		893	$! = Errno::ENXIO; $connect_cb->();
		894	}
		895	});
		896
		897	$hdl
		898	}
		899
		900	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		901	possibly after switching off other proxy types:
		902
		903	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		904
		905	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		906	my ($data, $headers) = @_;
		907	...
		908	};
559		909
560	=head1 SEE ALSO	910	=head1 SEE ALSO
561		911
562	L<AnyEvent>.	912	L<AnyEvent>.
563		913
564	=head1 AUTHOR	914	=head1 AUTHOR
565		915
566	Marc Lehmann <schmorp@schmorp.de>	916	Marc Lehmann <schmorp@schmorp.de>
567	http://home.schmorp.de/	917	http://home.schmorp.de/
568		918
		919	With many thanks to Дмитрий Шалашов, who provided countless
		920	testcases and bugreports.
		921
569	=cut	922	=cut
570		923
571	1	924	1
572		925

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.29 by root, Wed Oct 22 23:28:11 2008 UTC vs. Revision 1.60 by root, Thu Dec 30 02:56:28 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.29 by root, Wed Oct 22 23:28:11 2008 UTC vs.
Revision 1.60 by root, Thu Dec 30 02:56:28 2010 UTC