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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.52 by root, Sat Sep 26 10:13:12 2009 UTC vs.
Revision 1.66 by root, Fri Dec 31 06:18:30 2010 UTC

…		…
43		43
44	use Errno ();	44	use Errno ();
45		45
46	use AnyEvent 5.0 ();	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 = '1.43';	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	$headers->{Redirect}[1]{Redirect} >> will then contain the original
		121	response, and so on.
108		122
109	If the server sends a header multiple times, then their contents will be	123	If the server sends a header multiple times, then their contents will be
110	joined together with a comma (C<,>), as per the HTTP spec.	124	joined together with a comma (C<,>), as per the HTTP spec.
111		125
112	If an internal error occurs, such as not being able to resolve a hostname,	126	If an internal error occurs, such as not being able to resolve a hostname,
…		…
199	connect (for exmaple, to bind it on a given IP address). This parameter	213	connect (for exmaple, to bind it on a given IP address). This parameter
200	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>	214	overrides the prepare callback passed to C<AnyEvent::Socket::tcp_connect>
201	and behaves exactly the same way (e.g. it has to provide a	215	and behaves exactly the same way (e.g. it has to provide a
202	timeout). See the description for the C<$prepare_cb> argument of	216	timeout). See the description for the C<$prepare_cb> argument of
203	C<AnyEvent::Socket::tcp_connect> for details.	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.
204		230
205	=item on_header => $callback->($headers)	231	=item on_header => $callback->($headers)
206		232
207	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
208	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
…		…
326	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	352	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
327		353
328	_slot_schedule $_[0];	354	_slot_schedule $_[0];
329	}	355	}
330		356
331	our $qr_nl = qr{\015?\012};	357	# continue to parse $_ for headers and place them into the arg
		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
332	our $qr_nlnl = qr{(?<![^\012])\015?\012};	382	our $qr_nlnl = qr{(?<![^\012])\015?\012};
333		383
334	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	384	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
335	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	385	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
336		386
…		…
349	while (my ($k, $v) = each %$hdr) {	399	while (my ($k, $v) = each %$hdr) {
350	$hdr{lc $k} = $v;	400	$hdr{lc $k} = $v;
351	}	401	}
352	}	402	}
353		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
354	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	408	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
355		409
356	return $cb->(undef, { Status => 599, Reason => "Too many redirections", URL => $url })	410	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
357	if $recurse < 0;	411	if $recurse < 0;
358		412
359	my $proxy = $arg{proxy} \|\| $PROXY;	413	my $proxy = $arg{proxy} \|\| $PROXY;
360	my $timeout = $arg{timeout} \|\| $TIMEOUT;	414	my $timeout = $arg{timeout} \|\| $TIMEOUT;
361		415
362	my ($uscheme, $uauthority, $upath, $query, $fragment) =	416	my ($uscheme, $uauthority, $upath, $query, $fragment) =
363	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:\?([^#]))?(?:#(.))?\|;	417	$url =~ m\|(?:([^:/?#]+):)?(?://([^/?#]))?([^?#])(?:(\?[^#]))?(?:#(.))?\|;
364		418
365	$uscheme = lc $uscheme;	419	$uscheme = lc $uscheme;
366		420
367	my $uport = $uscheme eq "http" ? 80	421	my $uport = $uscheme eq "http" ? 80
368	: $uscheme eq "https" ? 443	422	: $uscheme eq "https" ? 443
369	: 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" });
370		424
371	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	425	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
372	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", URL => $url });	426	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
373		427
374	my $uhost = $1;	428	my $uhost = $1;
375	$uport = $2 if defined $2;	429	$uport = $2 if defined $2;
376		430
377	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost";	431	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
		432	unless exists $hdr{host};
378		433
379	$uhost =~ s/^\[(.*)\]$/$1/;	434	$uhost =~ s/^\[(.*)\]$/$1/;
380	$upath .= "?$query" if length $query;	435	$upath .= $query if length $query;
381		436
382	$upath =~ s%^/?%/%;	437	$upath =~ s%^/?%/%;
383		438
384	# cookie processing	439	# cookie processing
385	if (my $jar = $arg{cookie_jar}) {	440	if (my $jar = $arg{cookie_jar}) {
…		…
425	} else {	480	} else {
426	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	481	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
427	}	482	}
428		483
429	# leave out fragment and query string, just a heuristic	484	# leave out fragment and query string, just a heuristic
430	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};	485	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
431	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};	486	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
432		487
433	$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};
434		493
435	my %state = (connect_guard => 1);	494	my %state = (connect_guard => 1);
436		495
437	_get_slot $uhost, sub {	496	_get_slot $uhost, sub {
438	$state{slot_guard} = shift;	497	$state{slot_guard} = shift;
439		498
440	return unless $state{connect_guard};	499	return unless $state{connect_guard};
441		500
442	$state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {	501	my $connect_cb = sub {
443	$state{fh} = shift	502	$state{fh} = shift
444	or do {	503	or do {
445	my $err = "$!";	504	my $err = "$!";
446	%state = ();	505	%state = ();
447	return $cb->(undef, { Status => 599, Reason => $err, URL => $url });	506	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
448	};	507	};
449		508
450	pop; # free memory, save a tree	509	pop; # free memory, save a tree
451		510
452	return unless delete $state{connect_guard};	511	return unless delete $state{connect_guard};
453		512
454	# get handle	513	# get handle
455	$state{handle} = new AnyEvent::Handle	514	$state{handle} = new AnyEvent::Handle
456	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
457	timeout => $timeout,	519	timeout => $timeout,
458	peername => $rhost,	520	on_error => sub {
459	tls_ctx => $arg{tls_ctx};	521	%state = ();
		522	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
		523	},
		524	on_eof => sub {
		525	%state = ();
		526	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
		527	},
		528	;
460		529
461	# limit the number of persistent connections	530	# limit the number of persistent connections
462	# keepalive not yet supported	531	# keepalive not yet supported
463	if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	532	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
464	++$KA_COUNT{$_[1]};	533	# ++$KA_COUNT{$_[1]};
465	$state{handle}{ka_count_guard} = AnyEvent::Util::guard {	534	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
466	--$KA_COUNT{$_[1]}	535	# --$KA_COUNT{$_[1]}
467	};	536	# };
468	$hdr{connection} = "keep-alive";	537	# $hdr{connection} = "keep-alive";
469	} else {	538	# } else {
470	delete $hdr{connection};	539	# delete $hdr{connection};
471	}	540	# }
472
473	# (re-)configure handle
474	$state{handle}->on_error (sub {
475	%state = ();
476	$cb->(undef, { Status => 599, Reason => $_[2], URL => $url });
477	});
478	$state{handle}->on_eof (sub {
479	%state = ();
480	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", URL => $url });
481	});
482		541
483	$state{handle}->starttls ("connect") if $rscheme eq "https";	542	$state{handle}->starttls ("connect") if $rscheme eq "https";
484		543
485	# handle actual, non-tunneled, request	544	# handle actual, non-tunneled, request
486	my $handle_actual_request = sub {	545	my $handle_actual_request = sub {
487	$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};
488		547
489	# send request	548	# send request
490	$state{handle}->push_write (	549	$state{handle}->push_write (
491	"$method $rpath HTTP/1.0\015\012"	550	"$method $rpath HTTP/1.1\015\012"
492	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)	551	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
493	. "\015\012"	552	. "\015\012"
494	. (delete $arg{body})	553	. (delete $arg{body})
495	);	554	);
496		555
		556	# return if error occured during push_write()
		557	return unless %state;
		558
497	%hdr = (); # reduce memory usage, save a kitten	559	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
498		560
499	# status line	561	# status line and headers
500	$state{handle}->push_read (line => $qr_nl, sub {	562	$state{handle}->push_read (line => $qr_nlnl, sub {
501	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	563	my $keepalive = pop;
502	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response ($_[1])", URL => $url }));
503		564
504	my %hdr = ( # response headers
505	HTTPVersion => ",$1",
506	Status => ",$2",
507	Reason => ",$3",
508	URL => ",$url"
509	);
510
511	# headers, could be optimized a bit
512	$state{handle}->unshift_read (line => $qr_nlnl, sub {
513	for ("$_[1]") {	565	for ("$_[1]") {
514	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.
515		567
516	# things seen, not parsed:	568	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
517	# p3pP="NON CUR OTPi OUR NOR UNI"	569	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
518		570
519	$hdr{lc $1} .= ",$2"	571	push @pseudo,
520	while /\G	572	HTTPVersion => $1,
521	([^:\000-\037]*):	573	Status => $2,
522	[\011\040]*	574	Reason => $3,
523	((?: [^\012]+ \| \012[\011\040] )*)
524	\012
525	/gxc;
526
527	/\G$/	575	;
		576
		577	my $hdr = parse_hdr
528	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	$url =~ s/\/[^\/]*$//;
529	}	594	}
530		595
531	substr $_, 0, 1, ""
532	for values %hdr;
533
534	# redirect handling
535	# microsoft and other shitheads don't give a shit for following standards,
536	# try to support some common forms of broken Location headers.
537	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
538	$hdr{location} =~ s/^\.\/+//;
539
540	my $url = "$rscheme://$uhost:$uport";
541
542	unless ($hdr{location} =~ s/^\///) {
543	$url .= $upath;
544	$url =~ s/\/[^\/]*$//;
545	}
546
547	$hdr{location} = "$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;
548	}	615	}
		616	}
549		617
550	my $redirect;	618	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
		619	$state{handle}->destroy if $state{handle};
		620	%state = ();
551		621
		622	if (defined $_[1]) {
		623	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		624	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		625	}
		626
		627	# set-cookie processing
552	if ($recurse) {	628	if ($arg{cookie_jar}) {
553	if ($hdr{Status} =~ /^30[12]$/ && $method ne "POST") {	629	for ($hdr{"set-cookie"}) {
554	# apparently, mozilla et al. just change POST to GET here	630	# parse NAME=VALUE
555	# more research is needed before we do the same	631	my @kv;
		632
		633	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
556	$redirect = 1;	634	my $name = $1;
557	} elsif ($hdr{Status} == 303) {	635	my $value = $3;
558	# even http/1.1 is unclear on how to mutate the method	636
559	$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
560	$redirect = 1;	669	# store it
561	} elsif ($hdr{Status} == 307 && $method =~ /^(?:GET\|HEAD)$/) {	670	$arg{cookie_jar}{version} = 1;
562	$redirect = 1;	671	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		672
		673	redo if /\G\s*,/gc;
563	}	674	}
564	}	675	}
565		676
566	my $finish = sub {
567	$state{handle}->destroy if $state{handle};
568	%state = ();
569
570	# set-cookie processing
571	if ($arg{cookie_jar}) {
572	for ($_[1]{"set-cookie"}) {
573	# parse NAME=VALUE
574	my @kv;
575
576	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
577	my $name = $1;
578	my $value = $3;
579
580	unless ($value) {
581	$value = $2;
582	$value =~ s/\\(.)/$1/gs;
583	}
584
585	push @kv, $name => $value;
586
587	last unless /\G\s*;/gc;
588	}
589
590	last unless @kv;
591
592	my $name = shift @kv;
593	my %kv = (value => shift @kv, @kv);
594
595	my $cdom;
596	my $cpath = (delete $kv{path}) \|\| "/";
597
598	if (exists $kv{domain}) {
599	$cdom = delete $kv{domain};
600
601	$cdom =~ s/^\.?/./; # make sure it starts with a "."
602
603	next if $cdom =~ /\.$/;
604
605	# this is not rfc-like and not netscape-like. go figure.
606	my $ndots = $cdom =~ y/.//;
607	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
608	} else {
609	$cdom = $uhost;
610	}
611
612	# store it
613	$arg{cookie_jar}{version} = 1;
614	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
615
616	redo if /\G\s*,/gc;
617	}
618	}
619
620	if ($redirect && exists $hdr{location}) {	677	if ($redirect && exists $hdr{location}) {
621	# we ignore any errors, as it is very common to receive	678	# we ignore any errors, as it is very common to receive
622	# Content-Length != 0 but no actual body	679	# Content-Length != 0 but no actual body
623	# we also access %hdr, as $_[1] might be an erro	680	# we also access %hdr, as $_[1] might be an erro
624	http_request ($method => $hdr{location}, %arg, recurse => $recurse - 1, $cb);	681	http_request (
625	} else {	682	$method => $hdr{location},
626	$cb->($_[0], $_[1]);
627	}	683	%arg,
		684	recurse => $recurse - 1,
		685	Redirect => [$_[0], \%hdr],
628	};	686	$cb);
629
630	my $len = $hdr{"content-length"};
631
632	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
633	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", URL => $url });
634	} elsif (
635	$hdr{Status} =~ /^(?:1..\|[23]04)$/
636	or $method eq "HEAD"
637	or (defined $len && !$len)
638	) {
639	# no body
640	$finish->("", \%hdr);
641	} 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	$finish->("", undef, undef, 1);
		703	} else {
642	# body handling, four different code paths	704	# body handling, many different code paths
643	# for want_body_handle, on_body (2x), normal (2x)	705	# - no body expected
644	# we might read too much here, but it does not matter yet (no pers. connections)	706	# - want_body_handle
		707	# - te chunked
		708	# - 2x length known (with or without on_body)
		709	# - 2x length not known (with or without on_body)
645	if (!$redirect && $arg{want_body_handle}) {	710	if (!$redirect && $arg{want_body_handle}) {
646	$_[0]->on_eof (undef);	711	$_[0]->on_eof (undef);
647	$_[0]->on_error (undef);	712	$_[0]->on_error (undef);
648	$_[0]->on_read (undef);	713	$_[0]->on_read (undef);
649		714
650	$finish->(delete $state{handle}, \%hdr);	715	$finish->(delete $state{handle});
651		716
652	} elsif ($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
653	$_[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 $1;
		729
654	if ($len) {	730	if ($len) {
655	$_[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
656	$_[0]->on_read (sub {	735	$_[0]->push_read (line => sub {
657	$len -= length $_[0]{rbuf};	736	length $_[1]
658		737	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
659	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	738	$_[0]->push_read (line => $read_chunk);
660	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
661
662	$len > 0	739	});
663	or $finish->("", \%hdr);
664	});	740	});
665	} else {	741	} else {
666	$_[0]->on_eof (sub {	742	$_[0]->push_read (line => $qr_nlnl, sub {
667	$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	}
668	});	752	}
669	$_[0]->on_read (sub {	753
670	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	754	$finish->($body, undef, undef, 1);
671	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", URL => $url });
672	});	755	});
673	}	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	});
674	} else {	774	} else {
675	$_[0]->on_eof (undef);	775	$_[0]->on_eof (sub {
676		776	$finish->("");
677	if ($len) {	777	});
678	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], URL => $url }) });
679	$_[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 {
680	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)	789	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
681	if $len <= length $_[0]{rbuf};	790	if $len <= length $_[0]{rbuf};
682	});	791	});
683	} else {	792	} else {
684	$_[0]->on_error (sub {	793	$_[0]->on_error (sub {
685	$! == Errno::EPIPE \|\| !$!	794	($! == Errno::EPIPE \|\| !$!)
686	? $finish->(delete $_[0]{rbuf}, \%hdr)	795	? $finish->(delete $_[0]{rbuf})
687	: $finish->(undef, { Status => 599, Reason => $_[2], URL => $url });	796	: $finish->(undef, 599 => $_[2]);
688	});	797	});
689	$_[0]->on_read (sub { });	798	$_[0]->on_read (sub { });
690	}
691	}	799	}
692	}	800	}
693	});	801	}
694	});	802	});
695	};	803	};
696		804
697	# now handle proxy-CONNECT method	805	# now handle proxy-CONNECT method
698	if ($proxy && $uscheme eq "https") {	806	if ($proxy && $uscheme eq "https") {
…		…
700		808
701	# maybe re-use $uauthority with patched port?	809	# maybe re-use $uauthority with patched port?
702	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	810	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
703	$state{handle}->push_read (line => $qr_nlnl, sub {	811	$state{handle}->push_read (line => $qr_nlnl, sub {
704	$_[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
705	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])" }));
706		814
707	if ($2 == 200) {	815	if ($2 == 200) {
708	$rpath = $upath;	816	$rpath = $upath;
709	&$handle_actual_request;	817	&$handle_actual_request;
710	} else {	818	} else {
711	%state = ();	819	%state = ();
712	$cb->(undef, { Status => $2, Reason => $3, URL => $url });	820	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
713	}	821	}
714	});	822	});
715	} else {	823	} else {
716	&$handle_actual_request;	824	&$handle_actual_request;
717	}	825	}
		826	};
718		827
719	}, $arg{on_prepare} \|\| sub { $timeout };	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 { $timeout });
		832
720	};	833	};
721		834
722	defined wantarray && AnyEvent::Util::guard { %state = () }	835	defined wantarray && AnyEvent::Util::guard { %state = () }
723	}	836	}
724		837
…		…
738	&http_request	851	&http_request
739	}	852	}
740		853
741	=back	854	=back
742		855
		856	=head2 DNS CACHING
		857
		858	AnyEvent::HTTP uses the AnyEvent::Socket::tcp_connect function for
		859	the actual connection, which in turn uses AnyEvent::DNS to resolve
		860	hostnames. The latter is a simple stub resolver and does no caching
		861	on its own. If you want DNS caching, you currently have to provide
		862	your own default resolver (by storing a suitable resolver object in
		863	C<$AnyEvent::DNS::RESOLVER>).
		864
743	=head2 GLOBAL FUNCTIONS AND VARIABLES	865	=head2 GLOBAL FUNCTIONS AND VARIABLES
744		866
745	=over 4	867	=over 4
746		868
747	=item AnyEvent::HTTP::set_proxy "proxy-url"	869	=item AnyEvent::HTTP::set_proxy "proxy-url"
…		…
750	string of the form C<http://host:port> (optionally C<https:...>), croaks	872	string of the form C<http://host:port> (optionally C<https:...>), croaks
751	otherwise.	873	otherwise.
752		874
753	To clear an already-set proxy, use C<undef>.	875	To clear an already-set proxy, use C<undef>.
754		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.
		886
755	=item $AnyEvent::HTTP::MAX_RECURSE	887	=item $AnyEvent::HTTP::MAX_RECURSE
756		888
757	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>).
758		890
759	=item $AnyEvent::HTTP::USERAGENT	891	=item $AnyEvent::HTTP::USERAGENT
…		…
777	connections. This number of can be useful for load-leveling.	909	connections. This number of can be useful for load-leveling.
778		910
779	=back	911	=back
780		912
781	=cut	913	=cut
		914
		915	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		916	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		917
		918	sub format_date($) {
		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, $_, $y);
		952	}
		953	}
		954
		955	undef
		956	}
782		957
783	sub set_proxy($) {	958	sub set_proxy($) {
784	if (length $_[0]) {	959	if (length $_[0]) {
785	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	960	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
786	or Carp::croak "$_[0]: invalid proxy URL";	961	or Carp::croak "$_[0]: invalid proxy URL";
…		…
793	# initialise proxy from environment	968	# initialise proxy from environment
794	eval {	969	eval {
795	set_proxy $ENV{http_proxy};	970	set_proxy $ENV{http_proxy};
796	};	971	};
797		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	};
		1028
798	=head1 SEE ALSO	1029	=head1 SEE ALSO
799		1030
800	L<AnyEvent>.	1031	L<AnyEvent>.
801		1032
802	=head1 AUTHOR	1033	=head1 AUTHOR

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.52 by root, Sat Sep 26 10:13:12 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 1.52 by root, Sat Sep 26 10:13:12 2009 UTC vs.
Revision 1.66 by root, Fri Dec 31 06:18:30 2010 UTC