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

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.60 by root, Thu Dec 30 02:56:28 2010 UTC vs.
Revision 1.69 by root, Fri Dec 31 19:32:47 2010 UTC

…		…
47	use AnyEvent::Util ();	47	use AnyEvent::Util ();
48	use AnyEvent::Handle ();	48	use AnyEvent::Handle ();
49		49
50	use base Exporter::;	50	use base Exporter::;
51		51
52	our $VERSION = '1.46';	52	our $VERSION = '1.5';
53		53
54	our @EXPORT = qw(http_get http_post http_head http_request);	54	our @EXPORT = qw(http_get http_post http_head http_request);
55		55
56	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)";
57	our $MAX_RECURSE = 10;	57	our $MAX_RECURSE = 10;
…		…
94	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
95	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
96	destroyed before the callback is called, the request will be cancelled.	96	destroyed before the callback is called, the request will be cancelled.
97		97
98	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
99	(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
100	second argument.	100	(and trailers) as second argument.
101		101
102	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
103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible	103	headers, the "pseudo-headers" (uppercase to avoid clashing with possible
104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the	104	response headers) C<HTTPVersion>, C<Status> and C<Reason> contain the
105	three parts of the HTTP Status-Line of the same name.	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>.
106		109
107	The pseudo-header C<URL> contains the actual URL (which can differ from	110	The pseudo-header C<URL> contains the actual URL (which can differ from
108	the requested URL when following redirects - for example, you might get	111	the requested URL when following redirects - for example, you might get
109	an error that your URL scheme is not supported even though your URL is a	112	an error that your URL scheme is not supported even though your URL is a
110	valid http URL because it redirected to an ftp URL, in which case you can	113	valid http URL because it redirected to an ftp URL, in which case you can
…		…
147	Whether to recurse requests or not, e.g. on redirects, authentication	150	Whether to recurse requests or not, e.g. on redirects, authentication
148	retries and so on, and how often to do so.	151	retries and so on, and how often to do so.
149		152
150	=item headers => hashref	153	=item headers => hashref
151		154
152	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 own
153	own C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers	156	C<Host:>, C<Content-Length:>, C<Connection:> and C<Cookie:> headers and
154	and will provide defaults for C<User-Agent:> and C<Referer:> (this can be	157	will provide defaults at least for C<TE:>, C<Referer:> and C<User-Agent:>
155	suppressed by using C<undef> for these headers in which case they won't be	158	(this can be suppressed by using C<undef> for these headers in which case
156	sent at all).	159	they won't be sent at all).
157		160
158	=item timeout => $seconds	161	=item timeout => $seconds
159		162
160	The time-out to use for various stages - each connect attempt will reset	163	The time-out to use for various stages - each connect attempt will reset
161	the timeout, as will read or write activity, i.e. this is not an overall	164	the timeout, as will read or write activity, i.e. this is not an overall
…		…
171	C<$scheme> must be either missing, C<http> for HTTP or C<https> for	174	C<$scheme> must be either missing, C<http> for HTTP or C<https> for
172	HTTPS.	175	HTTPS.
173		176
174	=item body => $string	177	=item body => $string
175		178
176	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
177	this module might offer more options).	180	this module might offer more options).
178		181
179	=item cookie_jar => $hash_ref	182	=item cookie_jar => $hash_ref
180		183
181	Passing this parameter enables (simplified) cookie-processing, loosely	184	Passing this parameter enables (simplified) cookie-processing, loosely
…		…
189	Note that this cookie implementation is not of very high quality, nor	192	Note that this cookie implementation is not of very high quality, nor
190	meant to be complete. If you want complete cookie management you have to	193	meant to be complete. If you want complete cookie management you have to
191	do that on your own. C<cookie_jar> is meant as a quick fix to get some	194	do that on your own. C<cookie_jar> is meant as a quick fix to get some
192	cookie-using sites working. Cookies are a privacy disaster, do not use	195	cookie-using sites working. Cookies are a privacy disaster, do not use
193	them unless required to.	196	them unless required to.
		197
		198	When cookie processing is enabled, the C<Cookie:> and C<Set-Cookie:>
		199	headers will be ste and handled by this module, otherwise they will be
		200	left untouched.
194		201
195	=item tls_ctx => $scheme \| $tls_ctx	202	=item tls_ctx => $scheme \| $tls_ctx
196		203
197	Specifies the AnyEvent::TLS context to be used for https connections. This	204	Specifies the AnyEvent::TLS context to be used for https connections. This
198	parameter follows the same rules as the C<tls_ctx> parameter to	205	parameter follows the same rules as the C<tls_ctx> parameter to
…		…
237		244
238	This callback is useful, among other things, to quickly reject unwanted	245	This callback is useful, among other things, to quickly reject unwanted
239	content, which, if it is supposed to be rare, can be faster than first	246	content, which, if it is supposed to be rare, can be faster than first
240	doing a C<HEAD> request.	247	doing a C<HEAD> request.
241		248
		249	The downside is that cancelling the request makes it impossible to re-use
		250	the connection. Also, the C<on_header> callback will not receive any
		251	trailer (headers sent after the response body).
		252
242	Example: cancel the request unless the content-type is "text/html".	253	Example: cancel the request unless the content-type is "text/html".
243		254
244	on_header => sub {	255	on_header => sub {
245	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/	256	$_[0]{"content-type"} =~ /^text\/html\s*(?:;\|$)/
246	},	257	},
…		…
252	string instead of the body data.	263	string instead of the body data.
253		264
254	It has to return either true (in which case AnyEvent::HTTP will continue),	265	It has to return either true (in which case AnyEvent::HTTP will continue),
255	or false, in which case AnyEvent::HTTP will cancel the download (and call	266	or false, in which case AnyEvent::HTTP will cancel the download (and call
256	the completion callback with an error code of C<598>).	267	the completion callback with an error code of C<598>).
		268
		269	The downside to cancelling the request is that it makes it impossible to
		270	re-use the connection.
257		271
258	This callback is useful when the data is too large to be held in memory	272	This callback is useful when the data is too large to be held in memory
259	(so the callback writes it to a file) or when only some information should	273	(so the callback writes it to a file) or when only some information should
260	be extracted, or when the body should be processed incrementally.	274	be extracted, or when the body should be processed incrementally.
261		275
…		…
287	If you think you need this, first have a look at C<on_body>, to see if	301	If you think you need this, first have a look at C<on_body>, to see if
288	that doesn't solve your problem in a better way.	302	that doesn't solve your problem in a better way.
289		303
290	=back	304	=back
291		305
292	Example: make a simple HTTP GET request for http://www.nethype.de/	306	Example: do a simple HTTP GET request for http://www.nethype.de/ and print
		307	the response body.
293		308
294	http_request GET => "http://www.nethype.de/", sub {	309	http_request GET => "http://www.nethype.de/", sub {
295	my ($body, $hdr) = @_;	310	my ($body, $hdr) = @_;
296	print "$body\n";	311	print "$body\n";
297	};	312	};
298		313
299	Example: make a HTTP HEAD request on https://www.google.com/, use a	314	Example: do a HTTP HEAD request on https://www.google.com/, use a
300	timeout of 30 seconds.	315	timeout of 30 seconds.
301		316
302	http_request	317	http_request
303	GET => "https://www.google.com",	318	GET => "https://www.google.com",
304	timeout => 30,	319	timeout => 30,
…		…
307	use Data::Dumper;	322	use Data::Dumper;
308	print Dumper $hdr;	323	print Dumper $hdr;
309	}	324	}
310	;	325	;
311		326
312	Example: make another simple HTTP GET request, but immediately try to	327	Example: do another simple HTTP GET request, but immediately try to
313	cancel it.	328	cancel it.
314		329
315	my $request = http_request GET => "http://www.nethype.de/", sub {	330	my $request = http_request GET => "http://www.nethype.de/", sub {
316	my ($body, $hdr) = @_;	331	my ($body, $hdr) = @_;
317	print "$body\n";	332	print "$body\n";
…		…
349	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];	364	push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
350		365
351	_slot_schedule $_[0];	366	_slot_schedule $_[0];
352	}	367	}
353		368
		369	# continue to parse $_ for headers and place them into the arg
		370	sub parse_hdr() {
		371	my %hdr;
		372
		373	# things seen, not parsed:
		374	# p3pP="NON CUR OTPi OUR NOR UNI"
		375
		376	$hdr{lc $1} .= ",$2"
		377	while /\G
		378	([^:\000-\037]*):
		379	[\011\040]*
		380	((?: [^\012]+ \| \012[\011\040] )*)
		381	\012
		382	/gxc;
		383
		384	/\G$/
		385	or return;
		386
		387	# remove the "," prefix we added to all headers above
		388	substr $_, 0, 1, ""
		389	for values %hdr;
		390
		391	\%hdr
		392	}
		393
354	our $qr_nlnl = qr{(?<![^\012])\015?\012};	394	our $qr_nlnl = qr{(?<![^\012])\015?\012};
355		395
356	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };	396	our $TLS_CTX_LOW = { cache => 1, sslv2 => 1 };
357	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };	397	our $TLS_CTX_HIGH = { cache => 1, verify => 1, verify_peername => "https" };
358		398
…		…
377	my @pseudo = (URL => $url);	417	my @pseudo = (URL => $url);
378	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};	418	push @pseudo, Redirect => delete $arg{Redirect} if exists $arg{Redirect};
379		419
380	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;	420	my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
381		421
382	return $cb->(undef, { Status => 599, Reason => "Too many redirections", @pseudo })	422	return $cb->(undef, { @pseudo, Status => 599, Reason => "Too many redirections" })
383	if $recurse < 0;	423	if $recurse < 0;
384		424
385	my $proxy = $arg{proxy} \|\| $PROXY;	425	my $proxy = $arg{proxy} \|\| $PROXY;
386	my $timeout = $arg{timeout} \|\| $TIMEOUT;	426	my $timeout = $arg{timeout} \|\| $TIMEOUT;
387		427
…		…
390		430
391	$uscheme = lc $uscheme;	431	$uscheme = lc $uscheme;
392		432
393	my $uport = $uscheme eq "http" ? 80	433	my $uport = $uscheme eq "http" ? 80
394	: $uscheme eq "https" ? 443	434	: $uscheme eq "https" ? 443
395	: return $cb->(undef, { Status => 599, Reason => "Only http and https URL schemes supported", @pseudo });	435	: return $cb->(undef, { @pseudo, Status => 599, Reason => "Only http and https URL schemes supported" });
396		436
397	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x	437	$uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
398	or return $cb->(undef, { Status => 599, Reason => "Unparsable URL", @pseudo });	438	or return $cb->(undef, { @pseudo, Status => 599, Reason => "Unparsable URL" });
399		439
400	my $uhost = $1;	440	my $uhost = $1;
401	$uport = $2 if defined $2;	441	$uport = $2 if defined $2;
402		442
403	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"	443	$hdr{host} = defined $2 ? "$uhost:$2" : "$uhost"
…		…
452	} else {	492	} else {
453	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);	493	($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
454	}	494	}
455		495
456	# leave out fragment and query string, just a heuristic	496	# leave out fragment and query string, just a heuristic
457	$hdr{referer} \|\|= "$uscheme://$uauthority$upath" unless exists $hdr{referer};	497	$hdr{referer} = "$uscheme://$uauthority$upath" unless exists $hdr{referer};
458	$hdr{"user-agent"} \|\|= $USERAGENT unless exists $hdr{"user-agent"};	498	$hdr{"user-agent"} = $USERAGENT unless exists $hdr{"user-agent"};
459		499
460	$hdr{"content-length"} = length $arg{body}	500	$hdr{"content-length"} = length $arg{body}
461	if length $arg{body} \|\| $method ne "GET";	501	if length $arg{body} \|\| $method ne "GET";
462		502
		503	$hdr{connection} = "close TE"; #1.1
		504	$hdr{te} = "trailers" unless exists $hdr{te}; #1.1
		505
463	my %state = (connect_guard => 1);	506	my %state = (connect_guard => 1);
464		507
465	_get_slot $uhost, sub {	508	_get_slot $uhost, sub {
466	$state{slot_guard} = shift;	509	$state{slot_guard} = shift;
467		510
468	return unless $state{connect_guard};	511	return unless $state{connect_guard};
469		512
470	my $tcp_connect = $arg{tcp_connect}	513	my $connect_cb = sub {
471	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
472
473	$state{connect_guard} = $tcp_connect->(
474	$rhost,
475	$rport,
476	sub {
477	$state{fh} = shift	514	$state{fh} = shift
478	or do {	515	or do {
479	my $err = "$!";	516	my $err = "$!";
480	%state = ();	517	%state = ();
481	return $cb->(undef, { Status => 599, Reason => $err, @pseudo });	518	return $cb->(undef, { @pseudo, Status => 599, Reason => $err });
482	};	519	};
483		520
484	pop; # free memory, save a tree	521	pop; # free memory, save a tree
485		522
486	return unless delete $state{connect_guard};	523	return unless delete $state{connect_guard};
487		524
488	# get handle	525	# get handle
489	$state{handle} = new AnyEvent::Handle	526	$state{handle} = new AnyEvent::Handle
490	fh => $state{fh},	527	fh => $state{fh},
491	peername => $rhost,	528	peername => $rhost,
492	tls_ctx => $arg{tls_ctx},	529	tls_ctx => $arg{tls_ctx},
493	# these need to be reconfigured on keepalive handles	530	# these need to be reconfigured on keepalive handles
494	timeout => $timeout,	531	timeout => $timeout,
495	on_error => sub {	532	on_error => sub {
496	%state = ();	533	%state = ();
497	$cb->(undef, { Status => 599, Reason => $_[2], @pseudo });	534	$cb->(undef, { @pseudo, Status => 599, Reason => $_[2] });
498	},	535	},
499	on_eof => sub {	536	on_eof => sub {
500	%state = ();	537	%state = ();
501	$cb->(undef, { Status => 599, Reason => "Unexpected end-of-file", @pseudo });	538	$cb->(undef, { @pseudo, Status => 599, Reason => "Unexpected end-of-file" });
502	},	539	},
503	;	540	;
504		541
505	# limit the number of persistent connections	542	# limit the number of persistent connections
506	# keepalive not yet supported	543	# keepalive not yet supported
507	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {	544	# if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
508	# ++$KA_COUNT{$_[1]};	545	# ++$KA_COUNT{$_[1]};
509	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {	546	# $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
510	# --$KA_COUNT{$_[1]}	547	# --$KA_COUNT{$_[1]}
511	# };	548	# };
512	# $hdr{connection} = "keep-alive";	549	# $hdr{connection} = "keep-alive";
513	# } else {
514	delete $hdr{connection};
515	# }	550	# }
516		551
517	$state{handle}->starttls ("connect") if $rscheme eq "https";	552	$state{handle}->starttls ("connect") if $rscheme eq "https";
518		553
519	# handle actual, non-tunneled, request	554	# handle actual, non-tunneled, request
520	my $handle_actual_request = sub {	555	my $handle_actual_request = sub {
521	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};	556	$state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
522		557
523	# send request	558	# send request
524	$state{handle}->push_write (	559	$state{handle}->push_write (
525	"$method $rpath HTTP/1.0\015\012"	560	"$method $rpath HTTP/1.1\015\012"
526	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)	561	. (join "", map "\u$_: $hdr{$_}\015\012", grep defined $hdr{$_}, keys %hdr)
527	. "\015\012"	562	. "\015\012"
528	. (delete $arg{body})	563	. (delete $arg{body})
529	);	564	);
530		565
531	# return if error occured during push_write()	566	# return if error occured during push_write()
532	return unless %state;	567	return unless %state;
533		568
534	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use	569	%hdr = (); # reduce memory usage, save a kitten, also make it possible to re-use
535		570
536	# status line and headers	571	# status line and headers
537	$state{handle}->push_read (line => $qr_nlnl, sub {	572	$state{read_response} = sub {
538	for ("$_[1]") {	573	for ("$_[1]") {
539	y/\015//d; # weed out any \015, as they show up in the weirdest of places.	574	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
540		575
541	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )? \015?\012/igxc	576	/^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\012]*) )? \012/igxc
542	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid server response", @pseudo }));	577	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid server response" }));
543		578
		579	# 100 Continue handling
		580	# should not happen as we don't send expect: 100-continue,
		581	# but we handle it just in case.
		582	# since we send the request body regardless, if we get an error
		583	# we are out of-sync, which we currently do NOT handle correctly.
		584	return $state{handle}->push_read (line => $qr_nlnl, $state{read_response})
		585	if $2 eq 100;
		586
544	push @pseudo,	587	push @pseudo,
545	HTTPVersion => $1,	588	HTTPVersion => $1,
546	Status => $2,	589	Status => $2,
547	Reason => $3,	590	Reason => $3,
548	;	591	;
549		592
550	# things seen, not parsed:	593	my $hdr = parse_hdr
551	# p3pP="NON CUR OTPi OUR NOR UNI"
552
553	$hdr{lc $1} .= ",$2"
554	while /\G
555	([^:\000-\037]*):
556	[\011\040]*
557	((?: [^\012]+ \| \012[\011\040] )*)
558	\012
559	/gxc;
560
561	/\G$/
562	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Garbled response headers", @pseudo }));	594	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Garbled response headers" }));
		595
		596	%hdr = (%$hdr, @pseudo);
		597	}
		598
		599	# redirect handling
		600	# microsoft and other shitheads don't give a shit for following standards,
		601	# try to support some common forms of broken Location headers.
		602	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
		603	$hdr{location} =~ s/^\.\/+//;
		604
		605	my $url = "$rscheme://$uhost:$uport";
		606
		607	unless ($hdr{location} =~ s/^\///) {
		608	$url .= $upath;
		609	$url =~ s/\/[^\/]*$//;
563	}	610	}
564		611
565	# remove the "," prefix we added to all headers above
566	substr $_, 0, 1, ""
567	for values %hdr;
568
569	# patch in all pseudo headers
570	%hdr = (%hdr, @pseudo);
571
572	# redirect handling
573	# microsoft and other shitheads don't give a shit for following standards,
574	# try to support some common forms of broken Location headers.
575	if ($hdr{location} !~ /^(?: $ \| [^:\/?\#]+ : )/x) {
576	$hdr{location} =~ s/^\.\/+//;
577
578	my $url = "$rscheme://$uhost:$uport";
579
580	unless ($hdr{location} =~ s/^\///) {
581	$url .= $upath;
582	$url =~ s/\/[^\/]*$//;
583	}
584
585	$hdr{location} = "$url/$hdr{location}";	612	$hdr{location} = "$url/$hdr{location}";
		613	}
		614
		615	my $redirect;
		616
		617	if ($recurse) {
		618	my $status = $hdr{Status};
		619
		620	# industry standard is to redirect POST as GET for
		621	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
		622	# also, the UA should ask the user for 301 and 307 and POST,
		623	# industry standard seems to be to simply follow.
		624	# we go with the industry standard.
		625	if ($status == 301 or $status == 302 or $status == 303) {
		626	# HTTP/1.1 is unclear on how to mutate the method
		627	$method = "GET" unless $method eq "HEAD";
		628	$redirect = 1;
		629	} elsif ($status == 307) {
		630	$redirect = 1;
586	}	631	}
		632	}
587		633
		634	my $finish = sub { # ($data, $err_status, $err_reason[, $keepalive])
588	my $redirect;	635	my $keepalive = pop;
589		636
		637	$state{handle}->destroy if $state{handle};
		638	%state = ();
		639
		640	if (defined $_[1]) {
		641	$hdr{OrigStatus} = $hdr{Status}; $hdr{Status} = $_[1];
		642	$hdr{OrigReason} = $hdr{Reason}; $hdr{Reason} = $_[2];
		643	}
		644
		645	# set-cookie processing
590	if ($recurse) {	646	if ($arg{cookie_jar}) {
591	my $status = $hdr{Status};	647	for ($hdr{"set-cookie"}) {
		648	# parse NAME=VALUE
		649	my @kv;
592		650
593	# industry standard is to redirect POST as GET for	651	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
594	# 301, 302 and 303, in contrast to http/1.0 and 1.1.
595	# also, the UA should ask the user for 301 and 307 and POST,
596	# industry standard seems to be to simply follow.
597	# we go with the industry standard.
598	if ($status == 301 or $status == 302 or $status == 303) {
599	# HTTP/1.1 is unclear on how to mutate the method
600	$method = "GET" unless $method eq "HEAD";
601	$redirect = 1;	652	my $name = $1;
602	} elsif ($status == 307) {	653	my $value = $3;
		654
		655	unless ($value) {
		656	$value = $2;
		657	$value =~ s/\\(.)/$1/gs;
		658	}
		659
		660	push @kv, $name => $value;
		661
		662	last unless /\G\s*;/gc;
		663	}
		664
		665	last unless @kv;
		666
		667	my $name = shift @kv;
		668	my %kv = (value => shift @kv, @kv);
		669
		670	my $cdom;
		671	my $cpath = (delete $kv{path}) \|\| "/";
		672
		673	if (exists $kv{domain}) {
		674	$cdom = delete $kv{domain};
		675
		676	$cdom =~ s/^\.?/./; # make sure it starts with a "."
		677
		678	next if $cdom =~ /\.$/;
		679
		680	# this is not rfc-like and not netscape-like. go figure.
		681	my $ndots = $cdom =~ y/.//;
		682	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
		683	} else {
		684	$cdom = $uhost;
		685	}
		686
603	$redirect = 1;	687	# store it
		688	$arg{cookie_jar}{version} = 1;
		689	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
		690
		691	redo if /\G\s*,/gc;
604	}	692	}
605	}	693	}
606		694
607	my $finish = sub {
608	$state{handle}->destroy if $state{handle};
609	%state = ();
610
611	# set-cookie processing
612	if ($arg{cookie_jar}) {
613	for ($_[1]{"set-cookie"}) {
614	# parse NAME=VALUE
615	my @kv;
616
617	while (/\G\s* ([^=;,[:space:]]+) \s=\s (?: "((?:[^\\"]+\|\\.))" \| ([^=;,[:space:]]) )/gcxs) {
618	my $name = $1;
619	my $value = $3;
620
621	unless ($value) {
622	$value = $2;
623	$value =~ s/\\(.)/$1/gs;
624	}
625
626	push @kv, $name => $value;
627
628	last unless /\G\s*;/gc;
629	}
630
631	last unless @kv;
632
633	my $name = shift @kv;
634	my %kv = (value => shift @kv, @kv);
635
636	my $cdom;
637	my $cpath = (delete $kv{path}) \|\| "/";
638
639	if (exists $kv{domain}) {
640	$cdom = delete $kv{domain};
641
642	$cdom =~ s/^\.?/./; # make sure it starts with a "."
643
644	next if $cdom =~ /\.$/;
645
646	# this is not rfc-like and not netscape-like. go figure.
647	my $ndots = $cdom =~ y/.//;
648	next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
649	} else {
650	$cdom = $uhost;
651	}
652
653	# store it
654	$arg{cookie_jar}{version} = 1;
655	$arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
656
657	redo if /\G\s*,/gc;
658	}
659	}
660
661	if ($redirect && exists $hdr{location}) {	695	if ($redirect && exists $hdr{location}) {
662	# we ignore any errors, as it is very common to receive	696	# we ignore any errors, as it is very common to receive
663	# Content-Length != 0 but no actual body	697	# Content-Length != 0 but no actual body
664	# we also access %hdr, as $_[1] might be an erro	698	# we also access %hdr, as $_[1] might be an erro
665	http_request (	699	http_request (
666	$method => $hdr{location},	700	$method => $hdr{location},
667	%arg,	701	%arg,
668	recurse => $recurse - 1,	702	recurse => $recurse - 1,
669	Redirect => \@_,	703	Redirect => [$_[0], \%hdr],
670	$cb);	704	$cb);
671	} else {
672	$cb->($_[0], $_[1]);
673	}
674	};
675
676	my $len = $hdr{"content-length"};
677
678	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
679	$finish->(undef, { Status => 598, Reason => "Request cancelled by on_header", @pseudo });
680	} elsif (
681	$hdr{Status} =~ /^(?:1..\|[23]04)$/
682	or $method eq "HEAD"
683	or (defined $len && !$len)
684	) {
685	# no body
686	$finish->("", \%hdr);
687	} else {	705	} else {
		706	$cb->($_[0], \%hdr);
		707	}
		708	};
		709
		710	my $len = $hdr{"content-length"};
		711
		712	if (!$redirect && $arg{on_header} && !$arg{on_header}(\%hdr)) {
		713	$finish->(undef, 598 => "Request cancelled by on_header");
		714	} elsif (
		715	$hdr{Status} =~ /^(?:1..\|204\|205\|304)$/
		716	or $method eq "HEAD"
		717	or (defined $len && !$len)
		718	) {
		719	# no body
		720	$finish->("", undef, undef, 1);
		721	} else {
688	# body handling, four different code paths	722	# body handling, many different code paths
689	# for want_body_handle, on_body (2x), normal (2x)	723	# - no body expected
690	# we might read too much here, but it does not matter yet (no pers. connections)	724	# - want_body_handle
		725	# - te chunked
		726	# - 2x length known (with or without on_body)
		727	# - 2x length not known (with or without on_body)
691	if (!$redirect && $arg{want_body_handle}) {	728	if (!$redirect && $arg{want_body_handle}) {
692	$_[0]->on_eof (undef);	729	$_[0]->on_eof (undef);
693	$_[0]->on_error (undef);	730	$_[0]->on_error (undef);
694	$_[0]->on_read (undef);	731	$_[0]->on_read (undef);
695		732
696	$finish->(delete $state{handle}, \%hdr);	733	$finish->(delete $state{handle});
697		734
698	} elsif ($arg{on_body}) {	735	} elsif ($hdr{"transfer-encoding"} =~ /\bchunked\b/i) {
		736	my $cl = 0;
		737	my $body = undef;
		738	my $on_body = $arg{on_body} \|\| sub { $body .= shift; 1 };
		739
699	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });	740	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		741
		742	my $read_chunk; $read_chunk = sub {
		743	$_[1] =~ /^([0-9a-fA-F]+)/
		744	or $finish->(undef, 599 => "Garbled chunked transfer encoding");
		745
		746	my $len = hex $1;
		747
700	if ($len) {	748	if ($len) {
701	$_[0]->on_eof (undef);	749	$cl += $len;
		750
		751	$_[0]->push_read (chunk => $len, sub {
		752	$on_body->($_[1], \%hdr)
		753	or return $finish->(undef, 598 => "Request cancelled by on_body");
		754
702	$_[0]->on_read (sub {	755	$_[0]->push_read (line => sub {
703	$len -= length $_[0]{rbuf};	756	length $_[1]
704		757	and return $finish->(undef, 599 => "Garbled chunked transfer encoding");
705	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	758	$_[0]->push_read (line => $read_chunk);
706	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
707
708	$len > 0	759	});
709	or $finish->("", \%hdr);
710	});	760	});
711	} else {	761	} else {
712	$_[0]->on_eof (sub {	762	$hdr{"content-length"} \|\|= $cl;
713	$finish->("", \%hdr);	763
		764	$_[0]->push_read (line => $qr_nlnl, sub {
		765	if (length $_[1]) {
		766	for ("$_[1]") {
		767	y/\015//d; # weed out any \015, as they show up in the weirdest of places.
		768
		769	my $hdr = parse_hdr
		770	or return $finish->(undef, 599 => "Garbled response trailers");
		771
		772	%hdr = (%hdr, %$hdr);
		773	}
714	});	774	}
715	$_[0]->on_read (sub {	775
716	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)	776	$finish->($body, undef, undef, 1);
717	or $finish->(undef, { Status => 598, Reason => "Request cancelled by on_body", @pseudo });
718	});	777	});
719	}	778	}
		779	};
		780
		781	$_[0]->push_read (line => $read_chunk);
		782
		783	} elsif ($arg{on_body}) {
		784	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		785
		786	if ($len) {
		787	$_[0]->on_read (sub {
		788	$len -= length $_[0]{rbuf};
		789
		790	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		791	or return $finish->(undef, 598 => "Request cancelled by on_body");
		792
		793	$len > 0
		794	or $finish->("", undef, undef, 1);
		795	});
720	} else {	796	} else {
721	$_[0]->on_eof (undef);	797	$_[0]->on_eof (sub {
722		798	$finish->("");
723	if ($len) {	799	});
724	$_[0]->on_error (sub { $finish->(undef, { Status => 599, Reason => $_[2], @pseudo }) });
725	$_[0]->on_read (sub {	800	$_[0]->on_read (sub {
		801	$arg{on_body}(delete $_[0]{rbuf}, \%hdr)
		802	or $finish->(undef, 598 => "Request cancelled by on_body");
		803	});
		804	}
		805	} else {
		806	$_[0]->on_eof (undef);
		807
		808	if ($len) {
		809	$_[0]->on_error (sub { $finish->(undef, 599 => $_[2]) });
		810	$_[0]->on_read (sub {
726	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), \%hdr)	811	$finish->((substr delete $_[0]{rbuf}, 0, $len, ""), undef, undef, 1)
727	if $len <= length $_[0]{rbuf};	812	if $len <= length $_[0]{rbuf};
728	});	813	});
729	} else {	814	} else {
730	$_[0]->on_error (sub {	815	$_[0]->on_error (sub {
731	($! == Errno::EPIPE \|\| !$!)	816	($! == Errno::EPIPE \|\| !$!)
732	? $finish->(delete $_[0]{rbuf}, \%hdr)	817	? $finish->(delete $_[0]{rbuf})
733	: $finish->(undef, { Status => 599, Reason => $_[2], @pseudo });	818	: $finish->(undef, 599 => $_[2]);
734	});	819	});
735	$_[0]->on_read (sub { });	820	$_[0]->on_read (sub { });
736	}
737	}	821	}
738	}	822	}
739	});	823	}
740	};	824	};
741		825
		826	$state{handle}->push_read (line => $qr_nlnl, $state{read_response});
		827	};
		828
742	# now handle proxy-CONNECT method	829	# now handle proxy-CONNECT method
743	if ($proxy && $uscheme eq "https") {	830	if ($proxy && $uscheme eq "https") {
744	# oh dear, we have to wrap it into a connect request	831	# oh dear, we have to wrap it into a connect request
745		832
746	# maybe re-use $uauthority with patched port?	833	# maybe re-use $uauthority with patched port?
747	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");	834	$state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
748	$state{handle}->push_read (line => $qr_nlnl, sub {	835	$state{handle}->push_read (line => $qr_nlnl, sub {
749	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix	836	$_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
750	or return (%state = (), $cb->(undef, { Status => 599, Reason => "Invalid proxy connect response ($_[1])", @pseudo }));	837	or return (%state = (), $cb->(undef, { @pseudo, Status => 599, Reason => "Invalid proxy connect response ($_[1])" }));
751		838
752	if ($2 == 200) {	839	if ($2 == 200) {
753	$rpath = $upath;	840	$rpath = $upath;
754	&$handle_actual_request;	841	&$handle_actual_request;
755	} else {	842	} else {
756	%state = ();	843	%state = ();
757	$cb->(undef, { Status => $2, Reason => $3, @pseudo });	844	$cb->(undef, { @pseudo, Status => $2, Reason => $3 });
758	}
759	});	845	}
		846	});
760	} else {	847	} else {
761	&$handle_actual_request;	848	&$handle_actual_request;
762	}
763
764	},	849	}
765	$arg{on_prepare} \|\| sub { $timeout }
766	);	850	};
		851
		852	my $tcp_connect = $arg{tcp_connect}
		853	\|\| do { require AnyEvent::Socket; \&AnyEvent::Socket::tcp_connect };
		854
		855	$state{connect_guard} = $tcp_connect->($rhost, $rport, $connect_cb, $arg{on_prepare} \|\| sub { $timeout });
		856
767	};	857	};
768		858
769	defined wantarray && AnyEvent::Util::guard { %state = () }	859	defined wantarray && AnyEvent::Util::guard { %state = () }
770	}	860	}
771		861
…		…
806	string of the form C<http://host:port> (optionally C<https:...>), croaks	896	string of the form C<http://host:port> (optionally C<https:...>), croaks
807	otherwise.	897	otherwise.
808		898
809	To clear an already-set proxy, use C<undef>.	899	To clear an already-set proxy, use C<undef>.
810		900
		901	=item $date = AnyEvent::HTTP::format_date $timestamp
		902
		903	Takes a POSIX timestamp (seconds since the epoch) and formats it as a HTTP
		904	Date (RFC 2616).
		905
		906	=item $timestamp = AnyEvent::HTTP::parse_date $date
		907
		908	Takes a HTTP Date (RFC 2616) and returns the corresponding POSIX
		909	timestamp, or C<undef> if the date cannot be parsed.
		910
811	=item $AnyEvent::HTTP::MAX_RECURSE	911	=item $AnyEvent::HTTP::MAX_RECURSE
812		912
813	The default value for the C<recurse> request parameter (default: C<10>).	913	The default value for the C<recurse> request parameter (default: C<10>).
814		914
815	=item $AnyEvent::HTTP::USERAGENT	915	=item $AnyEvent::HTTP::USERAGENT
…		…
833	connections. This number of can be useful for load-leveling.	933	connections. This number of can be useful for load-leveling.
834		934
835	=back	935	=back
836		936
837	=cut	937	=cut
		938
		939	our @month = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec);
		940	our @weekday = qw(Sun Mon Tue Wed Thu Fri Sat);
		941
		942	sub format_date($) {
		943	my ($time) = @_;
		944
		945	# RFC 822/1123 format
		946	my ($S, $M, $H, $mday, $mon, $year, $wday, $yday, undef) = gmtime $time;
		947
		948	sprintf "%s, %02d %s %04d %02d:%02d:%02d GMT",
		949	$weekday[$wday], $mday, $month[$mon], $year + 1900,
		950	$H, $M, $S;
		951	}
		952
		953	sub parse_date($) {
		954	my ($date) = @_;
		955
		956	my ($d, $m, $y, $H, $M, $S);
		957
		958	if ($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$/) {
		959	# RFC 822/1123, required by RFC 2616
		960	($d, $m, $y, $H, $M, $S) = ($1, $2, $3, $4, $5, $6);
		961
		962	} elsif ($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$/) {
		963	# RFC 850
		964	($d, $m, $y, $H, $M, $S) = ($1, $2, $3 < 69 ? $3 + 2000 : $3 + 1900, $4, $5, $6);
		965
		966	} elsif ($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])$/) {
		967	# ISO C's asctime
		968	($d, $m, $y, $H, $M, $S) = ($2, $1, $6, $3, $4, $5);
		969	}
		970	# other formats fail in the loop below
		971
		972	for (0..11) {
		973	if ($m eq $month[$_]) {
		974	require Time::Local;
		975	return Time::Local::timegm ($S, $M, $H, $d, $_, $y);
		976	}
		977	}
		978
		979	undef
		980	}
838		981
839	sub set_proxy($) {	982	sub set_proxy($) {
840	if (length $_[0]) {	983	if (length $_[0]) {
841	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix	984	$_[0] =~ m%^(https?):// ([^:/]+) (?: : (\d*) )?%ix
842	or Carp::croak "$_[0]: invalid proxy URL";	985	or Carp::croak "$_[0]: invalid proxy URL";

Diff Legend

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

Comparing AnyEvent-HTTP/HTTP.pm (file contents): Revision 1.60 by root, Thu Dec 30 02:56:28 2010 UTC vs. Revision 1.69 by root, Fri Dec 31 19:32:47 2010 UTC

Diff Legend

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.60 by root, Thu Dec 30 02:56:28 2010 UTC vs.
Revision 1.69 by root, Fri Dec 31 19:32:47 2010 UTC