ViewVC Help
View File | Revision Log | Show Annotations | Download File
/cvs/AnyEvent-HTTP/HTTP.pm
(Generate patch)

Comparing AnyEvent-HTTP/HTTP.pm (file contents):
Revision 1.20 by root, Mon Jun 9 13:04:23 2008 UTC vs.
Revision 1.30 by root, Thu Oct 23 02:46:20 2008 UTC

… …
48use AnyEvent::Socket (); 48use AnyEvent::Socket ();
49use AnyEvent::Handle (); 49use AnyEvent::Handle ();
50 50
51use base Exporter::; 51use base Exporter::;
52 52
53our $VERSION = '1.01'; 53our $VERSION = '1.05';
54 54
55our @EXPORT = qw(http_get http_post http_head http_request); 55our @EXPORT = qw(http_get http_post http_head http_request);
56 56
57our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; 57our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
58our $MAX_RECURSE = 10; 58our $MAX_RECURSE = 10;
… …
71my %CO_SLOT; # number of open connections, and wait queue, per host 71my %CO_SLOT; # number of open connections, and wait queue, per host
72 72
73=item http_get $url, key => value..., $cb->($data, $headers) 73=item http_get $url, key => value..., $cb->($data, $headers)
74 74
75Executes an HTTP-GET request. See the http_request function for details on 75Executes an HTTP-GET request. See the http_request function for details on
76additional parameters. 76additional parameters and the return value.
77 77
78=item http_head $url, key => value..., $cb->($data, $headers) 78=item http_head $url, key => value..., $cb->($data, $headers)
79 79
80Executes an HTTP-HEAD request. See the http_request function for details on 80Executes an HTTP-HEAD request. See the http_request function for details
81additional parameters. 81on additional parameters and the return value.
82 82
83=item http_post $url, $body, key => value..., $cb->($data, $headers) 83=item http_post $url, $body, key => value..., $cb->($data, $headers)
84 84
85Executes an HTTP-POST request with a request body of C<$bod>. See the 85Executes an HTTP-POST request with a request body of C<$body>. See the
86http_request function for details on additional parameters. 86http_request function for details on additional parameters and the return
87value.
87 88
88=item http_request $method => $url, key => value..., $cb->($data, $headers) 89=item http_request $method => $url, key => value..., $cb->($data, $headers)
89 90
90Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL 91Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
91must be an absolute http or https URL. 92must be an absolute http or https URL.
93
94When called in void context, nothing is returned. In other contexts,
95C<http_request> returns a "cancellation guard" - you have to keep the
96object at least alive until the callback get called. If the object gets
97destroyed before the callbakc is called, the request will be cancelled.
92 98
93The callback will be called with the response data as first argument 99The callback will be called with the response data as first argument
94(or C<undef> if it wasn't available due to errors), and a hash-ref with 100(or C<undef> if it wasn't available due to errors), and a hash-ref with
95response headers as second argument. 101response headers as second argument.
96 102
… …
188 my ($body, $hdr) = @_; 194 my ($body, $hdr) = @_;
189 use Data::Dumper; 195 use Data::Dumper;
190 print Dumper $hdr; 196 print Dumper $hdr;
191 } 197 }
192 ; 198 ;
199
200Example: make another simple HTTP GET request, but immediately try to
201cancel it.
202
203 my $request = http_request GET => "http://www.nethype.de/", sub {
204 my ($body, $hdr) = @_;
205 print "$body\n";
206 };
207
208 undef $request;
193 209
194=cut 210=cut
195 211
196sub _slot_schedule; 212sub _slot_schedule;
197sub _slot_schedule($) { 213sub _slot_schedule($) {
… …
235 while (my ($k, $v) = each %$hdr) { 251 while (my ($k, $v) = each %$hdr) {
236 $hdr{lc $k} = $v; 252 $hdr{lc $k} = $v;
237 } 253 }
238 } 254 }
239 255
240 my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; 256 my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
241 257
242 return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) 258 return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })
243 if $recurse < 0; 259 if $recurse < 0;
244 260
245 my $proxy = $arg{proxy} || $PROXY; 261 my $proxy = $arg{proxy} || $PROXY;
… …
274 %$jar = () if $jar->{version} < 1; 290 %$jar = () if $jar->{version} < 1;
275 291
276 my @cookie; 292 my @cookie;
277 293
278 while (my ($chost, $v) = each %$jar) { 294 while (my ($chost, $v) = each %$jar) {
295 if ($chost =~ /^\./) {
279 next unless $chost eq substr $uhost, -length $chost; 296 next unless $chost eq substr $uhost, -length $chost;
280 next unless $chost =~ /^\./; 297 } elsif ($chost =~ /\./) {
298 next unless $chost eq $uhost;
299 } else {
300 next;
301 }
281 302
282 while (my ($cpath, $v) = each %$v) { 303 while (my ($cpath, $v) = each %$v) {
283 next unless $cpath eq substr $upath, 0, length $cpath; 304 next unless $cpath eq substr $upath, 0, length $cpath;
284 305
285 while (my ($k, $v) = each %$v) { 306 while (my ($k, $v) = each %$v) {
… …
355 376
356 %hdr = (); # reduce memory usage, save a kitten 377 %hdr = (); # reduce memory usage, save a kitten
357 378
358 # status line 379 # status line
359 $state{handle}->push_read (line => qr/\015?\012/, sub { 380 $state{handle}->push_read (line => qr/\015?\012/, sub {
360 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix 381 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
361 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url })); 382 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
362 383
363 my %hdr = ( # response headers 384 my %hdr = ( # response headers
364 HTTPVersion => "\x00$1", 385 HTTPVersion => "\x00$1",
365 Status => "\x00$2", 386 Status => "\x00$2",
… …
369 390
370 # headers, could be optimized a bit 391 # headers, could be optimized a bit
371 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { 392 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
372 for ("$_[1]\012") { 393 for ("$_[1]\012") {
373 # we support spaces in field names, as lotus domino 394 # we support spaces in field names, as lotus domino
374 # creates them. 395 # creates them (actually spaces around seperators
396 # are strictly allowed in http, they are a security issue).
375 $hdr{lc $1} .= "\x00$2" 397 $hdr{lc $1} .= "\x00$2"
376 while /\G 398 while /\G
377 ([^:\000-\037]+): 399 ([^:\000-\037]+):
378 [\011\040]* 400 [\011\040]*
379 ((?: [^\015\012]+ | \015?\012[\011\040] )*) 401 ((?: [^\015\012]+ | \015?\012[\011\040] )*)
… …
386 408
387 substr $_, 0, 1, "" 409 substr $_, 0, 1, ""
388 for values %hdr; 410 for values %hdr;
389 411
390 my $finish = sub { 412 my $finish = sub {
413 # TODO: use destroy method, when/if available
414 #$state{handle}->destroy;
415 $state{handle}->on_eof (undef);
416 $state{handle}->on_error (undef);
391 %state = (); 417 %state = ();
392 418
393 # set-cookie processing 419 # set-cookie processing
394 if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { 420 if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) {
395 for (split /\x00/, $hdr{"set-cookie"}) { 421 for (split /\x00/, $hdr{"set-cookie"}) {
396 my ($cookie, @arg) = split /;\s*/; 422 my ($cookie, @arg) = split /;\s*/;
397 my ($name, $value) = split /=/, $cookie, 2; 423 my ($name, $value) = split /=/, $cookie, 2;
398 my %kv = (value => $value, map { split /=/, $_, 2 } @arg); 424 my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
399 425
400 my $cdom = (delete $kv{domain}) || $uhost; 426 my $cdom;
401 my $cpath = (delete $kv{path}) || "/"; 427 my $cpath = (delete $kv{path}) || "/";
428
429 if (exists $kv{domain}) {
430 $cdom = delete $kv{domain};
402 431
403 $cdom =~ s/^.?/./; # make sure it starts with a "." 432 $cdom =~ s/^\.?/./; # make sure it starts with a "."
404 433
405 next if $cdom =~ /\.$/; 434 next if $cdom =~ /\.$/;
406 435
407 # this is not rfc-like and not netscape-like. go figure. 436 # this is not rfc-like and not netscape-like. go figure.
408 my $ndots = $cdom =~ y/.//; 437 my $ndots = $cdom =~ y/.//;
409 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); 438 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
439 } else {
440 $cdom = $uhost;
441 }
410 442
411 # store it 443 # store it
412 $arg{cookie_jar}{version} = 1; 444 $arg{cookie_jar}{version} = 1;
413 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; 445 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
414 } 446 }
415 } 447 }
416 448
417 if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {
418 # microsoft and other assholes don't give a shit for following standards, 449 # microsoft and other shitheads don't give a shit for following standards,
419 # try to support a common form of broken Location header. 450 # try to support some common forms of broken Location headers.
451 if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
452 $_[1]{location} =~ s/^\.\/+//;
453
420 $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; 454 my $url = "$scheme://$uhost:$uport";
421 455
456 unless ($_[1]{location} =~ s/^\///) {
457 $url .= $upath;
458 $url =~ s/\/[^\/]*$//;
459 }
460
461 $_[1]{location} = "$url/$_[1]{location}";
462 }
463
464 if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
465 # apparently, mozilla et al. just change POST to GET here
466 # more research is needed before we do the same
422 http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); 467 http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
468 } elsif ($_[1]{Status} == 303 && $recurse) {
469 # even http/1.1 is unclear on how to mutate the method
470 $method = "GET" unless $method eq "HEAD";
471 http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
472 } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) {
473 http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
423 } else { 474 } else {
424 $cb->($_[0], $_[1]); 475 $cb->($_[0], $_[1]);
425 } 476 }
426 }; 477 };
427 478
… …
466 unshift @_, "HEAD"; 517 unshift @_, "HEAD";
467 &http_request 518 &http_request
468} 519}
469 520
470sub http_post($$@) { 521sub http_post($$@) {
522 my $url = shift;
471 unshift @_, "POST", "body"; 523 unshift @_, "POST", $url, "body";
472 &http_request 524 &http_request
473} 525}
474 526
475=back 527=back
476 528

Diff Legend

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