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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.42 by root, Mon Jul 6 00:08:16 2009 UTC vs.
Revision 1.66 by root, Fri Dec 31 06:18:30 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 4.452 ();	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 = '1.12';	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;
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 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
		431	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		432	unless exists $hdr{host};
		433
360	$uhost =~ s/^\[(.*)\]$/$1/;	434	$uhost =~ s/^\[(.*)\]$/$1/;
361	$upath .= "?$query" if length $query;	435	$upath .= $query if length $query;
362		436
363	$upath =~ s%^/?%/%;	437	$upath =~ s%^/?%/%;
364		438
365	# cookie processing	439	# cookie processing
366	if (my $jar = $arg{cookie_jar}) {	440	if (my $jar = $arg{cookie_jar}) {
…		…
396	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path	470	my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
397		471
398	if ($proxy) {	472	if ($proxy) {
399	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);	473	($rpath, $rhost, $rport, $rscheme) = ($url, @$proxy);
400		474
		475	$rscheme = "http" unless defined $rscheme;
		476
401	# don't support https requests over https-proxy transport,	477	# don't support https requests over https-proxy transport,
402	# 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.
403	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";	479	$rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
404	} else {	480	} else {
405	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	481	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
406	}	482	}
407		483
408	$hdr{"user-agent"} \|\|= $USERAGENT;	484	# leave out fragment and query string, just a heuristic
409	$hdr{referer} \|\|= "$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"};
410		487
411	$hdr{host} = "$uhost:$uport";
412	$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};
413		493
414	my %state = (connect_guard => 1);	494	my %state = (connect_guard => 1);
415		495
416	_get_slot $uhost, sub {	496	_get_slot $uhost, sub {
417	$state{slot_guard} = shift;	497	$state{slot_guard} = shift;
418		498
419	return unless $state{connect_guard};	499	return unless $state{connect_guard};
420		500
421	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	501	my $connect_cb = sub {
422	$state{fh} = shift	502	$state{fh} = shift
423	or return (%state = (), $cb->(undef, { Status => 599, Reason => "$!", URL => $url }));	503	or do {
		504	my $err = "$!";
		505	%state = ();
		506	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
		507	};
		508
424	pop; # free memory, save a tree	509	pop; # free memory, save a tree
425		510
426	return unless delete $state{connect_guard};	511	return unless delete $state{connect_guard};
427		512
428	# get handle	513	# get handle
429	$state{handle} = new AnyEvent::Handle	514	$state{handle} = new AnyEvent::Handle
430	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
431	timeout => $timeout,	519	timeout => $timeout,
432	peername => $rhost,	520	on_error => sub {
433	tls_ctx => $arg{tls_ctx};	521	%state = ();
		522	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		523	},
		524	on_eof => sub {
		525	%state = ();
		526	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		527	},
		528	;
434		529
435	# limit the number of persistent connections	530	# limit the number of persistent connections
436	# keepalive not yet supported	531	# keepalive not yet supported
437	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	532	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
438	++$KA_COUNT{$_[1]};	533	# ++$KA_COUNT{$_[1]};
439	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	534	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
440	--$KA_COUNT{$_[1]}	535	# --$KA_COUNT{$_[1]}
441	};	536	# };
442	$hdr{connection} = "keep-alive";	537	# $hdr{connection} = "keep-alive";
443	} else {	538	# } else {
444	delete $hdr{connection};	539	# delete $hdr{connection};
445	}	540	# }
446
447	# (re-)configure handle
448	$state{handle}->on_error (sub {
449	%state = ();
450	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
451	});
452	$state{handle}->on_eof (sub {
453	%state = ();
454	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
455	});
456		541
457	$state{handle}->starttls ("connect") if $rscheme eq "https";	542	$state{handle}->starttls ("connect") if $rscheme eq "https";
458		543
459	# handle actual, non-tunneled, request	544	# handle actual, non-tunneled, request
460	my $handle_actual_request = sub {	545	my $handle_actual_request = sub {
461	$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};
462		547
463	# send request	548	# send request
464	$state{handle}->push_write (	549	$state{handle}->push_write (
465	"$method $rpath HTTP/1.0\015\012"	550	"$method $rpath HTTP/1.1\015\012"
466	. (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)	551	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
467	. "\015\012"	552	. "\015\012"
468	. (delete $arg{body})	553	. (delete $arg{body})
469	);	554	);
470		555
		556	# return if error occured during push_write()
		557	return unless %state;
		558
471	%hdr = (); # reduce memory usage, save a kitten	559	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
472		560
473	# status line	561	# status line and headers
474	$state{handle}->push_read (line => $qr_nl, sub {	562	$state{handle}->push_read (line => $qr_nlnl, sub {
475	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	563	my $keepalive = pop;
476	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
477		564
478	my %hdr = ( # response headers
479	HTTPVersion => ",$1",
480	Status => ",$2",
481	Reason => ",$3",
482	URL => ",$url"
483	);
484
485	# headers, could be optimized a bit
486	$state{handle}->unshift_read (line => $qr_nlnl, sub {
487	for ("$_[1]\012") {	565	for ("$_[1]") {
488	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.
489		567
490	# things seen, not parsed:	568	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
491	# p3pP="NON CUR OTPi OUR NOR UNI"	569	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
492		570
493	$hdr{lc $1} .= ",$2"	571	push @pseudo,
494	while /\G	572	HTTPVersion => $1,
495	([^:\000-\037]+):	573	Status => $2,
496	[\011\040]*	574	Reason => $3,
497	((?: [^\012]+ \| \012[\011\040] )*)
498	\012
499	/gxc;
500
501	/\G$/	575	;
		576
		577	my $hdr = parse_hdr
502	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	$url =~ s/\/[^\/]*$//;
503	}	594	}
504		595
505	substr $_, 0, 1, ""
506	for values %hdr;
507
508	# redirect handling
509	# microsoft and other shitheads don't give a shit for following standards,
510	# try to support some common forms of broken Location headers.
511	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
512	$hdr{location} =~ s/^\.\/+//;
513
514	my $url = "$rscheme://$uhost:$uport";
515
516	unless ($hdr{location} =~ s/^\///) {
517	$url .= $upath;
518	$url =~ s/\/[^\/]*$//;
519	}
520
521	$hdr{location} = "$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;
522	}	615	}
		616	}
523		617
524	my $redirect;	618	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		619	$state{handle}->destroy if $state{handle};
		620	%state = ();
525		621
		622	if (defined $_[1]) {
		623	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		624	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		625	}
		626
		627	# set-cookie processing
526	if ($recurse) {	628	if ($arg{cookie_jar}) {
527	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {	629	for ($hdr{"set-cookie"}) {
528	# apparently, mozilla et al. just change POST to GET here	630	# parse NAME=VALUE
529	# more research is needed before we do the same	631	my @kv;
		632
		633	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
530	$redirect = 1;	634	my $name = $1;
531	} elsif ($hdr{Status} == 303) {	635	my $value = $3;
532	# even http/1.1 is unclear on how to mutate the method	636
533	$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
534	$redirect = 1;	669	# store it
535	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {	670	$arg{cookie_jar}{version} = 1;
536	$redirect = 1;	671	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		672
		673	redo if /\G\s*,/gc;
537	}	674	}
538	}	675	}
539		676
540	my $finish = sub {	677	if ($redirect && exists $hdr{location}) {
541	$state{handle}->destroy if $state{handle};
542	%state = ();
543
544	# set-cookie processing
545	if ($arg{cookie_jar}) {
546	for ($_[1]{"set-cookie"}) {
547	# parse NAME=VALUE
548	my @kv;
549
550	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
551	my $name = $1;
552	my $value = $3;
553
554	unless ($value) {
555	$value = $2;
556	$value =~ s/\\(.)/$1/gs;
557	}
558
559	push @kv, $name => $value;
560
561	last unless /\G\s*;/gc;
562	}
563
564	last unless @kv;
565
566	my $name = shift @kv;
567	my %kv = (value => shift @kv, @kv);
568
569	my $cdom;
570	my $cpath = (delete $kv{path}) \|\| "/";
571
572	if (exists $kv{domain}) {
573	$cdom = delete $kv{domain};
574
575	$cdom =~ s/^\.?/./; # make sure it starts with a "."
576
577	next if $cdom =~ /\.$/;
578
579	# this is not rfc-like and not netscape-like. go figure.
580	my $ndots = $cdom =~ y/.//;
581	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
582	} else {
583	$cdom = $uhost;
584	}
585
586	# store it
587	$arg{cookie_jar}{version} = 1;
588	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
589
590	redo if /\G\s*,/gc;
591	}
592	}
593
594	if ($redirect) {
595	# we ignore any errors, as it is very common to receive	678	# we ignore any errors, as it is very common to receive
596	# Content-Length != 0 but no actual body	679	# Content-Length != 0 but no actual body
597	# we also access %hdr, as $_[1] might be an erro	680	# we also access %hdr, as $_[1] might be an erro
598	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);	681	http_request (
599	} else {	682	$method => $hdr{location},
600	$cb->($_[0], $_[1]);
601	}	683	%arg,
		684	recurse => $recurse - 1,
		685	Redirect => [$_[0], \%hdr],
602	};	686	$cb);
603
604	my $len = $hdr{"content-length"};
605
606	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
607	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
608	} elsif (
609	$hdr{Status} =~ /^(?:1..\|[23]04)$/
610	or $method eq "HEAD"
611	or (defined $len && !$len)
612	) {
613	# no body
614	$finish->("", \%hdr);
615	} 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	$finish->("", undef, undef, 1);
		703	} else {
616	# body handling, four different code paths	704	# body handling, many different code paths
617	# for want_body_handle, on_body (2x), normal (2x)	705	# - no body expected
618	# we might read too much here, but it does not matter yet (no pers. connections)	706	# - want_body_handle
		707	# - te chunked
		708	# - 2x length known (with or without on_body)
		709	# - 2x length not known (with or without on_body)
619	if (!$redirect && $arg{want_body_handle}) {	710	if (!$redirect && $arg{want_body_handle}) {
620	$_[0]->on_eof (undef);	711	$_[0]->on_eof (undef);
621	$_[0]->on_error (undef);	712	$_[0]->on_error (undef);
622	$_[0]->on_read (undef);	713	$_[0]->on_read (undef);
623		714
624	$finish->(delete $state{handle}, \%hdr);	715	$finish->(delete $state{handle});
625		716
626	} elsif ($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
627	$_[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	warn $_[1];#d#
		725	$_[1] =~ /^([0-9a-fA-F]+)/
		726	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		727
		728	my $len = hex $1;
		729
628	if ($len) {	730	if ($len) {
629	$_[0]->on_eof (undef);	731	$_[0]->push_read (chunk => hex $1, sub {
		732	$on_body->($_[1], \%hdr)
		733	or return $finish->(undef, 598 => "Request cancelled by on_body");
		734
630	$_[0]->on_read (sub {	735	$_[0]->push_read (line => sub {
631	$len -= length $_[0]{rbuf};	736	length $_[1]
632		737	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
633	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	738	$_[0]->push_read (line => $read_chunk);
634	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
635
636	$len > 0	739	});
637	or $finish->("", \%hdr);
638	});	740	});
639	} else {	741	} else {
640	$_[0]->on_eof (sub {	742	$_[0]->push_read (line => $qr_nlnl, sub {
641	$finish->("", \%hdr);	743	if (length $_[1]) {
		744	for ("$_[1]") {
		745	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		746
		747	my $hdr = parse_hdr
		748	or return $finish->(undef, 599 => "Garbled response trailers");
		749
		750	%hdr = (%hdr, %$hdr);
		751	}
642	});	752	}
643	$_[0]->on_read (sub {	753
644	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	754	$finish->($body, undef, undef, 1);
645	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
646	});	755	});
647	}	756	}
		757	};
		758
		759	$_[0]->push_read (line => $read_chunk);
		760
		761	} elsif ($arg{on_body}) {
		762	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		763
		764	if ($len) {
		765	$_[0]->on_read (sub {
		766	$len -= length $_[0]{rbuf};
		767
		768	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		769	or return $finish->(undef, 598 => "Request cancelled by on_body");
		770
		771	$len > 0
		772	or $finish->("", undef, undef, 1);
		773	});
648	} else {	774	} else {
649	$_[0]->on_eof (undef);	775	$_[0]->on_eof (sub {
650		776	$finish->("");
651	if ($len) {	777	});
652	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
653	$_[0]->on_read (sub {	778	$_[0]->on_read (sub {
		779	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		780	or $finish->(undef, 598 => "Request cancelled by on_body");
		781	});
		782	}
		783	} else {
		784	$_[0]->on_eof (undef);
		785
		786	if ($len) {
		787	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		788	$_[0]->on_read (sub {
654	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)	789	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
655	if $len <= length $_[0]{rbuf};	790	if $len <= length $_[0]{rbuf};
656	});	791	});
657	} else {	792	} else {
658	$_[0]->on_error (sub {	793	$_[0]->on_error (sub {
659	$! == Errno::EPIPE	794	($! == Errno::EPIPE \|\| !$!)
660	? $finish->(delete $_[0]{rbuf}, \%hdr)	795	? $finish->(delete $_[0]{rbuf})
661	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });	796	: $finish->(undef, 599 => $_[2]);
662	});	797	});
663	$_[0]->on_read (sub { });	798	$_[0]->on_read (sub { });
664	}
665	}	799	}
666	}	800	}
667	});	801	}
668	});	802	});
669	};	803	};
670		804
671	# now handle proxy-CONNECT method	805	# now handle proxy-CONNECT method
672	if ($proxy && $uscheme eq "https") {	806	if ($proxy && $uscheme eq "https") {
…		…
674		808
675	# maybe re-use $uauthority with patched port?	809	# maybe re-use $uauthority with patched port?
676	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	810	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
677	$state{handle}->push_read (line => $qr_nlnl, sub {	811	$state{handle}->push_read (line => $qr_nlnl, sub {
678	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	812	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
679	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", URL => $url }));	813	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
680		814
681	if ($2 == 200) {	815	if ($2 == 200) {
682	$rpath = $upath;	816	$rpath = $upath;
683	&$handle_actual_request;	817	&$handle_actual_request;
684	} else {	818	} else {
685	%state = ();	819	%state = ();
686	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	820	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
687	}	821	}
688	});	822	});
689	} else {	823	} else {
690	&$handle_actual_request;	824	&$handle_actual_request;
691	}	825	}
692
693	}, sub {
694	$timeout
695	};	826	};
		827
		828	my $tcp_connect = $arg{tcp_connect}
		829	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		830
		831	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		832
696	};	833	};
697		834
698	defined wantarray && AnyEvent::Util::guard { %state = () }	835	defined wantarray && AnyEvent::Util::guard { %state = () }
699	}	836	}
700		837
…		…
714	&http_request	851	&http_request
715	}	852	}
716		853
717	=back	854	=back
718		855
		856	=head2 DNS CACHING
		857
		858	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		859	the actual connection, which in turn uses AnyEvent::DNS to resolve
		860	hostnames. The latter is a simple stub resolver and does no caching
		861	on its own. If you want DNS caching, you currently have to provide
		862	your own default resolver (by storing a suitable resolver object in
		863	C<$AnyEvent::DNS::RESOLVER>).
		864
719	=head2 GLOBAL FUNCTIONS AND VARIABLES	865	=head2 GLOBAL FUNCTIONS AND VARIABLES
720		866
721	=over 4	867	=over 4
722		868
723	=item AnyEvent::HTTP::set_proxy "proxy-url"	869	=item AnyEvent::HTTP::set_proxy "proxy-url"
724		870
725	Sets the default proxy server to use. The proxy-url must begin with a	871	Sets the default proxy server to use. The proxy-url must begin with a
726	string of the form C<http://host:port> (optionally C<https:...>).	872	string of the form C<http://host:port> (optionally C<https:...>), croaks
		873	otherwise.
		874
		875	To clear an already-set proxy, use C<undef>.
		876
		877	=item $date = AnyEvent::HTTP::format_date $timestamp
		878
		879	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		880	Date (RFC 2616).
		881
		882	=item $timestamp = AnyEvent::HTTP::parse_date $date
		883
		884	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX
		885	timestamp, or C<undef> if the date cannot be parsed.
727		886
728	=item $AnyEvent::HTTP::MAX_RECURSE	887	=item $AnyEvent::HTTP::MAX_RECURSE
729		888
730	The default value for the C<recurse> request parameter (default: C<10>).	889	The default value for the C<recurse> request parameter (default: C<10>).
731		890
732	=item $AnyEvent::HTTP::USERAGENT	891	=item $AnyEvent::HTTP::USERAGENT
733		892
734	The default value for the C<User-Agent> header (the default is	893	The default value for the C<User-Agent> header (the default is
735	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).	894	C<Mozilla/5.0 (compatible; U; AnyEvent-HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)>).
736		895
737	=item $AnyEvent::HTTP::MAX_PERSISTENT	896	=item $AnyEvent::HTTP::MAX_PER_HOST
738		897
739	The maximum number of persistent connections to keep open (default: 8).	898	The maximum number of concurrent connections to the same host (identified
		899	by the hostname). If the limit is exceeded, then the additional requests
		900	are queued until previous connections are closed.
740		901
741	Not implemented currently.	902	The default value for this is C<4>, and it is highly advisable to not
742		903	increase it.
743	=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
744
745	The maximum time to cache a persistent connection, in seconds (default: 2).
746
747	Not implemented currently.
748		904
749	=item $AnyEvent::HTTP::ACTIVE	905	=item $AnyEvent::HTTP::ACTIVE
750		906
751	The number of active connections. This is not the number of currently	907	The number of active connections. This is not the number of currently
752	running requests, but the number of currently open and non-idle TCP	908	running requests, but the number of currently open and non-idle TCP
…		…
754		910
755	=back	911	=back
756		912
757	=cut	913	=cut
758		914
		915	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		916	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		917
		918	sub format_date($) {
		919	my ($time) = @_;
		920
		921	# RFC 822/1123 format
		922	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		923
		924	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		925	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		926	$H, $M, $S;
		927	}
		928
		929	sub parse_date($) {
		930	my ($date) = @_;
		931
		932	my ($d, $m, $y, $H, $M, $S);
		933
		934	if ($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$/) {
		935	# RFC 822/1123, required by RFC 2616
		936	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		937
		938	} elsif ($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$/) {
		939	# RFC 850
		940	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		941
		942	} elsif ($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])$/) {
		943	# ISO C's asctime
		944	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		945	}
		946	# other formats fail in the loop below
		947
		948	for (0..11) {
		949	if ($m eq $month[$_]) {
		950	require Time::Local;
		951	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		952	}
		953	}
		954
		955	undef
		956	}
		957
759	sub set_proxy($) {	958	sub set_proxy($) {
		959	if (length $_[0]) {
760	$PROXY = [$2, $3 \|\| 3128, $1] if $_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix;	960	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
		961	or Carp::croak "$_[0]: invalid proxy URL";
		962	$PROXY = [$2, $3 \|\| 3128, $1]
		963	} else {
		964	undef $PROXY;
		965	}
761	}	966	}
762		967
763	# initialise proxy from environment	968	# initialise proxy from environment
		969	eval {
764	set_proxy $ENV{http_proxy};	970	set_proxy $ENV{http_proxy};
		971	};
		972
		973	=head2 SOCKS PROXIES
		974
		975	Socks proxies are not directly supported by AnyEvent::HTTP. You can
		976	compile your perl to support socks, or use an external program such as
		977	F<socksify> (dante) or F<tsocks> to make your program use a socks proxy
		978	transparently.
		979
		980	Alternatively, for AnyEvent::HTTP only, you can use your own
		981	C<tcp_connect> function that does the proxy handshake - here is an example
		982	that works with socks4a proxies:
		983
		984	use Errno;
		985	use AnyEvent::Util;
		986	use AnyEvent::Socket;
		987	use AnyEvent::Handle;
		988
		989	# host, port and username of/for your socks4a proxy
		990	my $socks_host = "10.0.0.23";
		991	my $socks_port = 9050;
		992	my $socks_user = "";
		993
		994	sub socks4a_connect {
		995	my ($host, $port, $connect_cb, $prepare_cb) = @_;
		996
		997	my $hdl = new AnyEvent::Handle
		998	connect => [$socks_host, $socks_port],
		999	on_prepare => sub { $prepare_cb->($_[0]{fh}) },
		1000	on_error => sub { $connect_cb->() },
		1001	;
		1002
		1003	$hdl->push_write (pack "CCnNZZ", 4, 1, $port, 1, $socks_user, $host);
		1004
		1005	$hdl->push_read (chunk => 8, sub {
		1006	my ($hdl, $chunk) = @_;
		1007	my ($status, $port, $ipn) = unpack "xCna4", $chunk;
		1008
		1009	if ($status == 0x5a) {
		1010	$connect_cb->($hdl->{fh}, (format_address $ipn) . ":$port");
		1011	} else {
		1012	$! = Errno::ENXIO; $connect_cb->();
		1013	}
		1014	});
		1015
		1016	$hdl
		1017	}
		1018
		1019	Use C<socks4a_connect> instead of C<tcp_connect> when doing C<http_request>s,
		1020	possibly after switching off other proxy types:
		1021
		1022	AnyEvent::HTTP::set_proxy undef; # usually you do not want other proxies
		1023
		1024	http_get 'http://www.google.com', tcp_connect => \&socks4a_connect, sub {
		1025	my ($data, $headers) = @_;
		1026	...
		1027	};
765		1028
766	=head1 SEE ALSO	1029	=head1 SEE ALSO
767		1030
768	L<AnyEvent>.	1031	L<AnyEvent>.
769		1032

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.42 by root, Mon Jul 6 00:08:16 2009 UTC vs. Revision 1.66 by root, Fri Dec 31 06:18:30 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.42 by root, Mon Jul 6 00:08:16 2009 UTC vs.
Revision 1.66 by root, Fri Dec 31 06:18:30 2010 UTC