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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.44 by root, Tue Jul 7 00:15:32 2009 UTC vs.
Revision 1.67 by root, Fri Dec 31 06:18:54 2010 UTC

…		…
41	use strict;	41	use strict;
42	no warnings;	42	no warnings;
43		43
44	use Errno ();	44	use Errno ();
45		45
46	use AnyEvent 4.8 ();	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 = '1.4';	52	our $VERSION = '1.5';
54		53
55	our @EXPORT = qw(http_get http_post http_head http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
56		55
57	our $USERAGENT = "Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$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;
…		…
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 body data as first argument	98	The callback will be called with the response body data as first argument
100	(or C<undef> if an error occured), and a hash-ref with response headers as	99	(or C<undef> if an error occured), and a hash-ref with response headers as
101	second argument.	100	second argument.
102		101
103	All the headers in that hash are lowercased. In addition to the response	102	All the headers in that hash are lowercased. In addition to the response
104	headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
		104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
105	contain the three parts of the HTTP Status-Line of the same name. The	105	three parts of the HTTP Status-Line of the same name. If an error occurs
		106	during the body phase of a request, then the original C<Status> and
		107	C<Reason> values from the header are available as C<OrigStatus> and
		108	C<OrigReason>.
		109
106	pseudo-header C<URL> contains the original URL (which can differ from the	110	The pseudo-header C<URL> contains the actual URL (which can differ from
107	requested URL when following redirects).	111	the requested URL when following redirects - for example, you might get
		112	an error that your URL scheme is not supported even though your URL is a
		113	valid http URL because it redirected to an ftp URL, in which case you can
		114	look at the URL pseudo header).
		115
		116	The pseudo-header C<Redirect> only exists when the request was a result
		117	of an internal redirect. In that case it is an array reference with
		118	the C<($data, $headers)> from the redirect response. Note that this
		119	response could in turn be the result of a redirect itself, and C<<
		120	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
108		122
109	If the server sends a header multiple times, then their contents will be	123	If the server sends a header multiple times, then their contents will be
110	joined together with a comma (C<,>), as per the HTTP spec.	124	joined together with a comma (C<,>), as per the HTTP spec.
111		125
112	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
…		…
138		152
139	=item headers => hashref	153	=item headers => hashref
140		154
141	The request headers to use. Currently, C<http_request> may provide its	155	The request headers to use. Currently, C<http_request> may provide its
142	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	156	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers
143	and will provide defaults for C<User-Agent:> and C<Referer:>.	157	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be
		158	suppressed by using C<undef> for these headers in which case they won't be
		159	sent at all).
144		160
145	=item timeout => $seconds	161	=item timeout => $seconds
146		162
147	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
148	the timeout, as will read or write activity. Default timeout is 5 minutes.	164	the timeout, as will read or write activity, i.e. this is not an overall
		165	timeout.
		166
		167	Default timeout is 5 minutes.
149		168
150	=item proxy => [$host, $port[, $scheme]] or undef	169	=item proxy => [$host, $port[, $scheme]] or undef
151		170
152	Use the given http proxy for all requests. If not specified, then the	171	Use the given http proxy for all requests. If not specified, then the
153	default proxy (as specified by C<$ENV{http_proxy}>) is used.	172	default proxy (as specified by C<$ENV{http_proxy}>) is used.
154		173
155	C<$scheme> must be either missing or C<http> for HTTP, or C<https> for	174	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
156	HTTPS.	175	HTTPS.
157		176
158	=item body => $string	177	=item body => $string
159		178
160	The request body, usually empty. Will be-sent as-is (future versions of	179	The request body, usually empty. Will be-sent as-is (future versions of
…		…
186	verification) TLS context.	205	verification) TLS context.
187		206
188	The default for this option is C<low>, which could be interpreted as "give	207	The default for this option is C<low>, which could be interpreted as "give
189	me the page, no matter what".	208	me the page, no matter what".
190		209
		210	=item on_prepare => $callback->($fh)
		211
		212	In rare cases you need to "tune" the socket before it is used to
		213	connect (for exmaple, to bind it on a given IP address). This parameter
		214	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
		215	and behaves exactly the same way (e.g. it has to provide a
		216	timeout). See the description for the C<$prepare_cb> argument of
		217	C<AnyEvent::Socket::tcp_connect> for details.
		218
		219	=item tcp_connect => $callback->($host, $service, $connect_cb, $prepare_cb)
		220
		221	In even rarer cases you want total control over how AnyEvent::HTTP
		222	establishes connections. Normally it uses L<AnyEvent::Socket::tcp_connect>
		223	to do this, but you can provide your own C<tcp_connect> function -
		224	obviously, it has to follow the same calling conventions, except that it
		225	may always return a connection guard object.
		226
		227	There are probably lots of weird uses for this function, starting from
		228	tracing the hosts C<http_request> actually tries to connect, to (inexact
		229	but fast) host => IP address caching or even socks protocol support.
		230
191	=item on_header => $callback->($headers)	231	=item on_header => $callback->($headers)
192		232
193	When specified, this callback will be called with the header hash as soon	233	When specified, this callback will be called with the header hash as soon
194	as headers have been successfully received from the remote server (not on	234	as headers have been successfully received from the remote server (not on
195	locally-generated errors).	235	locally-generated errors).
…		…
221	This callback is useful when the data is too large to be held in memory	261	This callback is useful when the data is too large to be held in memory
222	(so the callback writes it to a file) or when only some information should	262	(so the callback writes it to a file) or when only some information should
223	be extracted, or when the body should be processed incrementally.	263	be extracted, or when the body should be processed incrementally.
224		264
225	It is usually preferred over doing your own body handling via	265	It is usually preferred over doing your own body handling via
226	C<want_body_handle>.	266	C<want_body_handle>, but in case of streaming APIs, where HTTP is
		267	only used to create a connection, C<want_body_handle> is the better
		268	alternative, as it allows you to install your own event handler, reducing
		269	resource usage.
227		270
228	=item want_body_handle => $enable	271	=item want_body_handle => $enable
229		272
230	When enabled (default is disabled), the behaviour of AnyEvent::HTTP	273	When enabled (default is disabled), the behaviour of AnyEvent::HTTP
231	changes considerably: after parsing the headers, and instead of	274	changes considerably: after parsing the headers, and instead of
…		…
243	This is useful with some push-type services, where, after the initial	286	This is useful with some push-type services, where, after the initial
244	headers, an interactive protocol is used (typical example would be the	287	headers, an interactive protocol is used (typical example would be the
245	push-style twitter API which starts a JSON/XML stream).	288	push-style twitter API which starts a JSON/XML stream).
246		289
247	If you think you need this, first have a look at C<on_body>, to see if	290	If you think you need this, first have a look at C<on_body>, to see if
248	that doesn'T solve your problem in a better way.	291	that doesn't solve your problem in a better way.
249		292
250	=back	293	=back
251		294
252	Example: make a simple HTTP GET request for http://www.nethype.de/	295	Example: make a simple HTTP GET request for http://www.nethype.de/
253		296
…		…
309	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	352	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
310		353
311	_slot_schedule $_[0];	354	_slot_schedule $_[0];
312	}	355	}
313		356
314	our $qr_nl = qr<\015?\012>;	357	# continue to parse $_ for headers and place them into the arg
315	our $qr_nlnl = qr<\015?\012\015?\012>;	358	sub parse_hdr() {
		359	my %hdr;
		360
		361	# things seen, not parsed:
		362	# p3pP="NON CUR OTPi OUR NOR UNI"
		363
		364	$hdr{lc $1} .= ",$2"
		365	while /\G
		366	([^:\000-\037]*):
		367	[\011\040]*
		368	((?: [^\012]+ \| \012[\011\040] )*)
		369	\012
		370	/gxc;
		371
		372	/\G$/
		373	or return;
		374
		375	# remove the "," prefix we added to all headers above
		376	substr $_, 0, 1, ""
		377	for values %hdr;
		378
		379	\%hdr
		380	}
		381
		382	our $qr_nlnl = qr{(?<![^\012])\015?\012};
316		383
317	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	384	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
318	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	385	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
319		386
320	sub http_request($$@) {	387	sub http_request($$@) {
…		…
332	while (my ($k, $v) = each %$hdr) {	399	while (my ($k, $v) = each %$hdr) {
333	$hdr{lc $k} = $v;	400	$hdr{lc $k} = $v;
334	}	401	}
335	}	402	}
336		403
		404	# pseudo headers for all subsequent responses
		405	my @pseudo = (URL => $url);
		406	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
		407
337	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	408	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
338		409
339	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })	410	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
340	if $recurse < 0;	411	if $recurse < 0;
341		412
342	my $proxy = $arg{proxy} \|\| $PROXY;	413	my $proxy = $arg{proxy} \|\| $PROXY;
343	my $timeout = $arg{timeout} \|\| $TIMEOUT;	414	my $timeout = $arg{timeout} \|\| $TIMEOUT;
344		415
345	my ($uscheme, $uauthority, $upath, $query, $fragment) =	416	my ($uscheme, $uauthority, $upath, $query, $fragment) =
346	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	417	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
347		418
348	$uscheme = lc $uscheme;	419	$uscheme = lc $uscheme;
349		420
350	my $uport = $uscheme eq "http" ? 80	421	my $uport = $uscheme eq "http" ? 80
351	: $uscheme eq "https" ? 443	422	: $uscheme eq "https" ? 443
352	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", URL => $url });	423	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
353		424
354	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	425	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
355	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });	426	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
356		427
357	my $uhost = $1;	428	my $uhost = $1;
358	$uport = $2 if defined $2;	429	$uport = $2 if defined $2;
359		430
360	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost";	431	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		432	unless exists $hdr{host};
361		433
362	$uhost =~ s/^\[(.*)\]$/$1/;	434	$uhost =~ s/^\[(.*)\]$/$1/;
363	$upath .= "?$query" if length $query;	435	$upath .= $query if length $query;
364		436
365	$upath =~ s%^/?%/%;	437	$upath =~ s%^/?%/%;
366		438
367	# cookie processing	439	# cookie processing
368	if (my $jar = $arg{cookie_jar}) {	440	if (my $jar = $arg{cookie_jar}) {
…		…
398	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	470	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
399		471
400	if ($proxy) {	472	if ($proxy) {
401	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);	473	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
402		474
		475	$rscheme = "http" unless defined $rscheme;
		476
403	# don't support https requests over https-proxy transport,	477	# don't support https requests over https-proxy transport,
404	# can't be done with tls as spec'ed, unless you double-encrypt.	478	# can't be done with tls as spec'ed, unless you double-encrypt.
405	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	479	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
406	} else {	480	} else {
407	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	481	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
408	}	482	}
409		483
410	$hdr{"user-agent"} \|\|= $USERAGENT;	484	# leave out fragment and query string, just a heuristic
411	$hdr{referer} \|\|= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic	485	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
		486	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
412		487
413	$hdr{"content-length"} = length $arg{body};	488	$hdr{"content-length"} = length $arg{body}
		489	if length $arg{body} \|\| $method ne "GET";
		490
		491	$hdr{connection} = "close TE";
		492	$hdr{te} = "trailers" unless exists $hdr{te};
414		493
415	my %state = (connect_guard => 1);	494	my %state = (connect_guard => 1);
416		495
417	_get_slot $uhost, sub {	496	_get_slot $uhost, sub {
418	$state{slot_guard} = shift;	497	$state{slot_guard} = shift;
419		498
420	return unless $state{connect_guard};	499	return unless $state{connect_guard};
421		500
422	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	501	my $connect_cb = sub {
423	$state{fh} = shift	502	$state{fh} = shift
424	or do {	503	or do {
425	my $err = "$!";	504	my $err = "$!";
426	%state = ();	505	%state = ();
427	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });	506	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
428	};	507	};
429		508
430	pop; # free memory, save a tree	509	pop; # free memory, save a tree
431		510
432	return unless delete $state{connect_guard};	511	return unless delete $state{connect_guard};
433		512
434	# get handle	513	# get handle
435	$state{handle} = new AnyEvent::Handle	514	$state{handle} = new AnyEvent::Handle
436	fh => $state{fh},	515	fh => $state{fh},
		516	peername => $rhost,
		517	tls_ctx => $arg{tls_ctx},
		518	# these need to be reconfigured on keepalive handles
437	timeout => $timeout,	519	timeout => $timeout,
438	peername => $rhost,	520	on_error => sub {
439	tls_ctx => $arg{tls_ctx};	521	%state = ();
		522	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		523	},
		524	on_eof => sub {
		525	%state = ();
		526	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		527	},
		528	;
440		529
441	# limit the number of persistent connections	530	# limit the number of persistent connections
442	# keepalive not yet supported	531	# keepalive not yet supported
443	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	532	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
444	++$KA_COUNT{$_[1]};	533	# ++$KA_COUNT{$_[1]};
445	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	534	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
446	--$KA_COUNT{$_[1]}	535	# --$KA_COUNT{$_[1]}
447	};	536	# };
448	$hdr{connection} = "keep-alive";	537	# $hdr{connection} = "keep-alive";
449	} else {	538	# } else {
450	delete $hdr{connection};	539	# delete $hdr{connection};
451	}	540	# }
452
453	# (re-)configure handle
454	$state{handle}->on_error (sub {
455	%state = ();
456	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
457	});
458	$state{handle}->on_eof (sub {
459	%state = ();
460	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
461	});
462		541
463	$state{handle}->starttls ("connect") if $rscheme eq "https";	542	$state{handle}->starttls ("connect") if $rscheme eq "https";
464		543
465	# handle actual, non-tunneled, request	544	# handle actual, non-tunneled, request
466	my $handle_actual_request = sub {	545	my $handle_actual_request = sub {
467	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	546	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
468		547
469	# send request	548	# send request
470	$state{handle}->push_write (	549	$state{handle}->push_write (
471	"$method $rpath HTTP/1.0\015\012"	550	"$method $rpath HTTP/1.1\015\012"
472	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	551	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
473	. "\015\012"	552	. "\015\012"
474	. (delete $arg{body})	553	. (delete $arg{body})
475	);	554	);
476		555
		556	# return if error occured during push_write()
		557	return unless %state;
		558
477	%hdr = (); # reduce memory usage, save a kitten	559	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
478		560
479	# status line	561	# status line and headers
480	$state{handle}->push_read (line => $qr_nl, sub {	562	$state{handle}->push_read (line => $qr_nlnl, sub {
481	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	563	my $keepalive = pop;
482	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
483		564
484	my %hdr = ( # response headers
485	HTTPVersion => ",$1",
486	Status => ",$2",
487	Reason => ",$3",
488	URL => ",$url"
489	);
490
491	# headers, could be optimized a bit
492	$state{handle}->unshift_read (line => $qr_nlnl, sub {
493	for ("$_[1]\012") {	565	for ("$_[1]") {
494	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	566	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
495		567
496	# things seen, not parsed:	568	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
497	# p3pP="NON CUR OTPi OUR NOR UNI"	569	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
498		570
499	$hdr{lc $1} .= ",$2"	571	push @pseudo,
500	while /\G	572	HTTPVersion => $1,
501	([^:\000-\037]*):	573	Status => $2,
502	[\011\040]*	574	Reason => $3,
503	((?: [^\012]+ \| \012[\011\040] )*)
504	\012
505	/gxc;
506
507	/\G$/	575	;
		576
		577	my $hdr = parse_hdr
508	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", URL => $url }));	578	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		579
		580	%hdr = (%$hdr, @pseudo);
		581	}
		582
		583	# redirect handling
		584	# microsoft and other shitheads don't give a shit for following standards,
		585	# try to support some common forms of broken Location headers.
		586	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		587	$hdr{location} =~ s/^\.\/+//;
		588
		589	my $url = "$rscheme://$uhost:$uport";
		590
		591	unless ($hdr{location} =~ s/^\///) {
		592	$url .= $upath;
		593	$url =~ s/\/[^\/]*$//;
509	}	594	}
510		595
511	substr $_, 0, 1, ""
512	for values %hdr;
513
514	# redirect handling
515	# microsoft and other shitheads don't give a shit for following standards,
516	# try to support some common forms of broken Location headers.
517	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
518	$hdr{location} =~ s/^\.\/+//;
519
520	my $url = "$rscheme://$uhost:$uport";
521
522	unless ($hdr{location} =~ s/^\///) {
523	$url .= $upath;
524	$url =~ s/\/[^\/]*$//;
525	}
526
527	$hdr{location} = "$url/$hdr{location}";	596	$hdr{location} = "$url/$hdr{location}";
		597	}
		598
		599	my $redirect;
		600
		601	if ($recurse) {
		602	my $status = $hdr{Status};
		603
		604	# industry standard is to redirect POST as GET for
		605	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		606	# also, the UA should ask the user for 301 and 307 and POST,
		607	# industry standard seems to be to simply follow.
		608	# we go with the industry standard.
		609	if ($status == 301 or $status == 302 or $status == 303) {
		610	# HTTP/1.1 is unclear on how to mutate the method
		611	$method = "GET" unless $method eq "HEAD";
		612	$redirect = 1;
		613	} elsif ($status == 307) {
		614	$redirect = 1;
528	}	615	}
		616	}
529		617
530	my $redirect;	618	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		619	$state{handle}->destroy if $state{handle};
		620	%state = ();
531		621
		622	if (defined $_[1]) {
		623	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		624	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		625	}
		626
		627	# set-cookie processing
532	if ($recurse) {	628	if ($arg{cookie_jar}) {
533	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {	629	for ($hdr{"set-cookie"}) {
534	# apparently, mozilla et al. just change POST to GET here	630	# parse NAME=VALUE
535	# more research is needed before we do the same	631	my @kv;
		632
		633	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
536	$redirect = 1;	634	my $name = $1;
537	} elsif ($hdr{Status} == 303) {	635	my $value = $3;
538	# even http/1.1 is unclear on how to mutate the method	636
539	$method = "GET" unless $method eq "HEAD";	637	unless ($value) {
		638	$value = $2;
		639	$value =~ s/\\(.)/$1/gs;
		640	}
		641
		642	push @kv, $name => $value;
		643
		644	last unless /\G\s*;/gc;
		645	}
		646
		647	last unless @kv;
		648
		649	my $name = shift @kv;
		650	my %kv = (value => shift @kv, @kv);
		651
		652	my $cdom;
		653	my $cpath = (delete $kv{path}) \|\| "/";
		654
		655	if (exists $kv{domain}) {
		656	$cdom = delete $kv{domain};
		657
		658	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		659
		660	next if $cdom =~ /\.$/;
		661
		662	# this is not rfc-like and not netscape-like. go figure.
		663	my $ndots = $cdom =~ y/.//;
		664	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		665	} else {
		666	$cdom = $uhost;
		667	}
		668
540	$redirect = 1;	669	# store it
541	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {	670	$arg{cookie_jar}{version} = 1;
542	$redirect = 1;	671	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		672
		673	redo if /\G\s*,/gc;
543	}	674	}
544	}	675	}
545		676
546	my $finish = sub {	677	if ($redirect && exists $hdr{location}) {
547	$state{handle}->destroy if $state{handle};
548	%state = ();
549
550	# set-cookie processing
551	if ($arg{cookie_jar}) {
552	for ($_[1]{"set-cookie"}) {
553	# parse NAME=VALUE
554	my @kv;
555
556	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
557	my $name = $1;
558	my $value = $3;
559
560	unless ($value) {
561	$value = $2;
562	$value =~ s/\\(.)/$1/gs;
563	}
564
565	push @kv, $name => $value;
566
567	last unless /\G\s*;/gc;
568	}
569
570	last unless @kv;
571
572	my $name = shift @kv;
573	my %kv = (value => shift @kv, @kv);
574
575	my $cdom;
576	my $cpath = (delete $kv{path}) \|\| "/";
577
578	if (exists $kv{domain}) {
579	$cdom = delete $kv{domain};
580
581	$cdom =~ s/^\.?/./; # make sure it starts with a "."
582
583	next if $cdom =~ /\.$/;
584
585	# this is not rfc-like and not netscape-like. go figure.
586	my $ndots = $cdom =~ y/.//;
587	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
588	} else {
589	$cdom = $uhost;
590	}
591
592	# store it
593	$arg{cookie_jar}{version} = 1;
594	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
595
596	redo if /\G\s*,/gc;
597	}
598	}
599
600	if ($redirect) {
601	# we ignore any errors, as it is very common to receive	678	# we ignore any errors, as it is very common to receive
602	# Content-Length != 0 but no actual body	679	# Content-Length != 0 but no actual body
603	# we also access %hdr, as $_[1] might be an erro	680	# we also access %hdr, as $_[1] might be an erro
604	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);	681	http_request (
605	} else {	682	$method => $hdr{location},
606	$cb->($_[0], $_[1]);
607	}	683	%arg,
		684	recurse => $recurse - 1,
		685	Redirect => [$_[0], \%hdr],
608	};	686	$cb);
609
610	my $len = $hdr{"content-length"};
611
612	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
613	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
614	} elsif (
615	$hdr{Status} =~ /^(?:1..\|[23]04)$/
616	or $method eq "HEAD"
617	or (defined $len && !$len)
618	) {
619	# no body
620	$finish->("", \%hdr);
621	} else {	687	} else {
		688	$cb->($_[0], \%hdr);
		689	}
		690	};
		691
		692	my $len = $hdr{"content-length"};
		693
		694	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		695	$finish->(undef, 598 => "Request cancelled by on_header");
		696	} elsif (
		697	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		698	or $method eq "HEAD"
		699	or (defined $len && !$len)
		700	) {
		701	# no body
		702	$finish->("", undef, undef, 1);
		703	} else {
622	# body handling, four different code paths	704	# body handling, many different code paths
623	# for want_body_handle, on_body (2x), normal (2x)	705	# - no body expected
624	# we might read too much here, but it does not matter yet (no pers. connections)	706	# - want_body_handle
		707	# - te chunked
		708	# - 2x length known (with or without on_body)
		709	# - 2x length not known (with or without on_body)
625	if (!$redirect && $arg{want_body_handle}) {	710	if (!$redirect && $arg{want_body_handle}) {
626	$_[0]->on_eof (undef);	711	$_[0]->on_eof (undef);
627	$_[0]->on_error (undef);	712	$_[0]->on_error (undef);
628	$_[0]->on_read (undef);	713	$_[0]->on_read (undef);
629		714
630	$finish->(delete $state{handle}, \%hdr);	715	$finish->(delete $state{handle});
631		716
632	} elsif ($arg{on_body}) {	717	} elsif ($hdr{"transfer-encoding"} =~ /chunked/) {
		718	my $body = undef;
		719	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		720
633	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });	721	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		722
		723	my $read_chunk; $read_chunk = sub {
		724	$_[1] =~ /^([0-9a-fA-F]+)/
		725	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		726
		727	my $len = hex $1;
		728
634	if ($len) {	729	if ($len) {
635	$_[0]->on_eof (undef);	730	$_[0]->push_read (chunk => hex $1, sub {
		731	$on_body->($_[1], \%hdr)
		732	or return $finish->(undef, 598 => "Request cancelled by on_body");
		733
636	$_[0]->on_read (sub {	734	$_[0]->push_read (line => sub {
637	$len -= length $_[0]{rbuf};	735	length $_[1]
638		736	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
639	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	737	$_[0]->push_read (line => $read_chunk);
640	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
641
642	$len > 0	738	});
643	or $finish->("", \%hdr);
644	});	739	});
645	} else {	740	} else {
646	$_[0]->on_eof (sub {	741	$_[0]->push_read (line => $qr_nlnl, sub {
647	$finish->("", \%hdr);	742	if (length $_[1]) {
		743	for ("$_[1]") {
		744	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		745
		746	my $hdr = parse_hdr
		747	or return $finish->(undef, 599 => "Garbled response trailers");
		748
		749	%hdr = (%hdr, %$hdr);
		750	}
648	});	751	}
649	$_[0]->on_read (sub {	752
650	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	753	$finish->($body, undef, undef, 1);
651	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
652	});	754	});
653	}	755	}
		756	};
		757
		758	$_[0]->push_read (line => $read_chunk);
		759
		760	} elsif ($arg{on_body}) {
		761	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		762
		763	if ($len) {
		764	$_[0]->on_read (sub {
		765	$len -= length $_[0]{rbuf};
		766
		767	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		768	or return $finish->(undef, 598 => "Request cancelled by on_body");
		769
		770	$len > 0
		771	or $finish->("", undef, undef, 1);
		772	});
654	} else {	773	} else {
655	$_[0]->on_eof (undef);	774	$_[0]->on_eof (sub {
656		775	$finish->("");
657	if ($len) {	776	});
658	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
659	$_[0]->on_read (sub {	777	$_[0]->on_read (sub {
		778	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		779	or $finish->(undef, 598 => "Request cancelled by on_body");
		780	});
		781	}
		782	} else {
		783	$_[0]->on_eof (undef);
		784
		785	if ($len) {
		786	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		787	$_[0]->on_read (sub {
660	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)	788	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
661	if $len <= length $_[0]{rbuf};	789	if $len <= length $_[0]{rbuf};
662	});	790	});
663	} else {	791	} else {
664	$_[0]->on_error (sub {	792	$_[0]->on_error (sub {
665	$! == Errno::EPIPE \|\| !$!	793	($! == Errno::EPIPE \|\| !$!)
666	? $finish->(delete $_[0]{rbuf}, \%hdr)	794	? $finish->(delete $_[0]{rbuf})
667	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });	795	: $finish->(undef, 599 => $_[2]);
668	});	796	});
669	$_[0]->on_read (sub { });	797	$_[0]->on_read (sub { });
670	}
671	}	798	}
672	}	799	}
673	});	800	}
674	});	801	});
675	};	802	};
676		803
677	# now handle proxy-CONNECT method	804	# now handle proxy-CONNECT method
678	if ($proxy && $uscheme eq "https") {	805	if ($proxy && $uscheme eq "https") {
…		…
680		807
681	# maybe re-use $uauthority with patched port?	808	# maybe re-use $uauthority with patched port?
682	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	809	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
683	$state{handle}->push_read (line => $qr_nlnl, sub {	810	$state{handle}->push_read (line => $qr_nlnl, sub {
684	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	811	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
685	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));	812	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
686		813
687	if ($2 == 200) {	814	if ($2 == 200) {
688	$rpath = $upath;	815	$rpath = $upath;
689	&$handle_actual_request;	816	&$handle_actual_request;
690	} else {	817	} else {
691	%state = ();	818	%state = ();
692	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	819	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
693	}	820	}
694	});	821	});
695	} else {	822	} else {
696	&$handle_actual_request;	823	&$handle_actual_request;
697	}	824	}
698
699	}, sub {
700	$timeout
701	};	825	};
		826
		827	my $tcp_connect = $arg{tcp_connect}
		828	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		829
		830	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		831
702	};	832	};
703		833
704	defined wantarray && AnyEvent::Util::guard { %state = () }	834	defined wantarray && AnyEvent::Util::guard { %state = () }
705	}	835	}
706		836
…		…
720	&http_request	850	&http_request
721	}	851	}
722		852
723	=back	853	=back
724		854
		855	=head2 DNS CACHING
		856
		857	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		858	the actual connection, which in turn uses AnyEvent::DNS to resolve
		859	hostnames. The latter is a simple stub resolver and does no caching
		860	on its own. If you want DNS caching, you currently have to provide
		861	your own default resolver (by storing a suitable resolver object in
		862	C<$AnyEvent::DNS::RESOLVER>).
		863
725	=head2 GLOBAL FUNCTIONS AND VARIABLES	864	=head2 GLOBAL FUNCTIONS AND VARIABLES
726		865
727	=over 4	866	=over 4
728		867
729	=item AnyEvent::HTTP::set_proxy "proxy-url"	868	=item AnyEvent::HTTP::set_proxy "proxy-url"
730		869
731	Sets the default proxy server to use. The proxy-url must begin with a	870	Sets the default proxy server to use. The proxy-url must begin with a
732	string of the form C<http://host:port> (optionally C<https:...>).	871	string of the form C<http://host:port> (optionally C<https:...>), croaks
		872	otherwise.
		873
		874	To clear an already-set proxy, use C<undef>.
		875
		876	=item $date = AnyEvent::HTTP::format_date $timestamp
		877
		878	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		879	Date (RFC 2616).
		880
		881	=item $timestamp = AnyEvent::HTTP::parse_date $date
		882
		883	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX
		884	timestamp, or C<undef> if the date cannot be parsed.
733		885
734	=item $AnyEvent::HTTP::MAX_RECURSE	886	=item $AnyEvent::HTTP::MAX_RECURSE
735		887
736	The default value for the C<recurse> request parameter (default: C<10>).	888	The default value for the C<recurse> request parameter (default: C<10>).
737		889
…		…
740	The default value for the C<User-Agent> header (the default is	892	The default value for the C<User-Agent> header (the default is
741	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	893	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
742		894
743	=item $AnyEvent::HTTP::MAX_PER_HOST	895	=item $AnyEvent::HTTP::MAX_PER_HOST
744		896
745	The maximum number of concurrent conenctions to the same host (identified	897	The maximum number of concurrent connections to the same host (identified
746	by the hostname). If the limit is exceeded, then the additional requests	898	by the hostname). If the limit is exceeded, then the additional requests
747	are queued until previous connections are closed.	899	are queued until previous connections are closed.
748		900
749	The default value for this is C<4>, and it is highly advisable to not	901	The default value for this is C<4>, and it is highly advisable to not
750	increase it.	902	increase it.
…		…
757		909
758	=back	910	=back
759		911
760	=cut	912	=cut
761		913
		914	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		915	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		916
		917	sub format_date($) {
		918	my ($time) = @_;
		919
		920	# RFC 822/1123 format
		921	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		922
		923	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		924	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		925	$H, $M, $S;
		926	}
		927
		928	sub parse_date($) {
		929	my ($date) = @_;
		930
		931	my ($d, $m, $y, $H, $M, $S);
		932
		933	if ($date =~ /^[A-Z][a-z][a-z], ([0-9][0-9]) ([A-Z][a-z][a-z]) ([0-9][0-9][0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) {
		934	# RFC 822/1123, required by RFC 2616
		935	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		936
		937	} elsif ($date =~ /^[A-Z][a-z]+, ([0-9][0-9])-([A-Z][a-z][a-z])-([0-9][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) GMT$/) {
		938	# RFC 850
		939	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		940
		941	} elsif ($date =~ /^[A-Z][a-z][a-z] ([A-Z][a-z][a-z]) ([0-9 ][0-9]) ([0-9][0-9]):([0-9][0-9]):([0-9][0-9]) ([0-9][0-9][0-9][0-9])$/) {
		942	# ISO C's asctime
		943	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		944	}
		945	# other formats fail in the loop below
		946
		947	for (0..11) {
		948	if ($m eq $month[$_]) {
		949	require Time::Local;
		950	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		951	}
		952	}
		953
		954	undef
		955	}
		956
762	sub set_proxy($) {	957	sub set_proxy($) {
		958	if (length $_[0]) {
763	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	959	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		960	or Carp::croak "$_[0]: invalid proxy URL";
		961	$PROXY = [$2, $3 \|\| 3128, $1]
		962	} else {
		963	undef $PROXY;
		964	}
764	}	965	}
765		966
766	# initialise proxy from environment	967	# initialise proxy from environment
		968	eval {
767	set_proxy $ENV{http_proxy};	969	set_proxy $ENV{http_proxy};
		970	};
		971
		972	=head2 SOCKS PROXIES
		973
		974	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		975	compile your perl to support socks, or use an external program such as
		976	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		977	transparently.
		978
		979	Alternatively, for AnyEvent::HTTP only, you can use your own
		980	C<tcp_connect> function that does the proxy handshake - here is an example
		981	that works with socks4a proxies:
		982
		983	use Errno;
		984	use AnyEvent::Util;
		985	use AnyEvent::Socket;
		986	use AnyEvent::Handle;
		987
		988	# host, port and username of/for your socks4a proxy
		989	my $socks_host = "10.0.0.23";
		990	my $socks_port = 9050;
		991	my $socks_user = "";
		992
		993	sub socks4a_connect {
		994	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		995
		996	my $hdl = new AnyEvent::Handle
		997	connect => [$socks_host, $socks_port],
		998	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		999	on_error => sub { $connect_cb->() },
		1000	;
		1001
		1002	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1003
		1004	$hdl->push_read (chunk => 8, sub {
		1005	my ($hdl, $chunk) = @_;
		1006	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1007
		1008	if ($status == 0x5a) {
		1009	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1010	} else {
		1011	$! = Errno::ENXIO; $connect_cb->();
		1012	}
		1013	});
		1014
		1015	$hdl
		1016	}
		1017
		1018	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1019	possibly after switching off other proxy types:
		1020
		1021	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1022
		1023	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1024	my ($data, $headers) = @_;
		1025	...
		1026	};
768		1027
769	=head1 SEE ALSO	1028	=head1 SEE ALSO
770		1029
771	L<AnyEvent>.	1030	L<AnyEvent>.
772		1031

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.44 by root, Tue Jul 7 00:15:32 2009 UTC vs. Revision 1.67 by root, Fri Dec 31 06:18:54 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.44 by root, Tue Jul 7 00:15:32 2009 UTC vs.
Revision 1.67 by root, Fri Dec 31 06:18:54 2010 UTC