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 1.18 by root, Fri Jun 6 16:23:57 2008 UTC vs.
Revision 1.29 by root, Wed Oct 22 23:28:11 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<$method> (e.g. C<GET>, C<POST>). The URL
91must be an absolute http or https URL. 92must be an absolute http or https URL.
93
94When called in void context, nothing is returned. In other contexts,
95C<http_request> returns a "cancellation guard" - you have to keep the
96object at least alive until the callback get called. If the object gets
97destroyed before the callbakc is called, the request will be cancelled.
92 98
93The callback will be called with the response data as first argument 99The callback will be called with the response data as first argument
94(or C<undef> if it wasn't available due to errors), and a hash-ref with 100(or C<undef> if it wasn't available due to errors), and a hash-ref with
95response headers as second argument. 101response headers as second argument.
96 102
97All the headers in that hash are lowercased. In addition to the response 103All the headers in that hash are lowercased. In addition to the response
98headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and 104headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>
99C<Reason> contain the three parts of the HTTP Status-Line of the same 105contain the three parts of the HTTP Status-Line of the same name. The
106pseudo-header C<URL> contains the original URL (which can differ from the
107requested URL when following redirects).
108
100name. If the server sends a header multiple lines, then their contents 109If the server sends a header multiple lines, then their contents will be
101will be joined together with C<\x00>. 110joined together with C<\x00>.
102 111
103If an internal error occurs, such as not being able to resolve a hostname, 112If an internal error occurs, such as not being able to resolve a hostname,
104then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> 113then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>
105and the C<Reason> pseudo-header will contain an error message. 114and the C<Reason> pseudo-header will contain an error message.
106 115
… …
185 my ($body, $hdr) = @_; 194 my ($body, $hdr) = @_;
186 use Data::Dumper; 195 use Data::Dumper;
187 print Dumper $hdr; 196 print Dumper $hdr;
188 } 197 }
189 ; 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 $request;
190 209
191=cut 210=cut
192 211
193sub _slot_schedule; 212sub _slot_schedule;
194sub _slot_schedule($) { 213sub _slot_schedule($) {
… …
232 while (my ($k, $v) = each %$hdr) { 251 while (my ($k, $v) = each %$hdr) {
233 $hdr{lc $k} = $v; 252 $hdr{lc $k} = $v;
234 } 253 }
235 } 254 }
236 255
237 my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; 256 my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
238 257
239 return $cb->(undef, { Status => 599, Reason => "recursion limit reached" }) 258 return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })
240 if $recurse < 0; 259 if $recurse < 0;
241 260
242 my $proxy = $arg{proxy} || $PROXY; 261 my $proxy = $arg{proxy} || $PROXY;
243 my $timeout = $arg{timeout} || $TIMEOUT; 262 my $timeout = $arg{timeout} || $TIMEOUT;
244 263
… …
249 268
250 $scheme = lc $scheme; 269 $scheme = lc $scheme;
251 270
252 my $uport = $scheme eq "http" ? 80 271 my $uport = $scheme eq "http" ? 80
253 : $scheme eq "https" ? 443 272 : $scheme eq "https" ? 443
254 : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" }); 273 : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });
255 274
256 $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic 275 $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic
257 276
258 $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x 277 $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
259 or return $cb->(undef, { Status => 599, Reason => "unparsable URL" }); 278 or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });
260 279
261 my $uhost = $1; 280 my $uhost = $1;
262 $uport = $2 if defined $2; 281 $uport = $2 if defined $2;
263 282
264 $uhost =~ s/^\[(.*)\]$/$1/; 283 $uhost =~ s/^\[(.*)\]$/$1/;
… …
309 328
310 return unless $state{connect_guard}; 329 return unless $state{connect_guard};
311 330
312 $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { 331 $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
313 $state{fh} = shift 332 $state{fh} = shift
314 or return $cb->(undef, { Status => 599, Reason => "$!" }); 333 or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });
315 334
316 delete $state{connect_guard}; # reduce memory usage, save a tree 335 delete $state{connect_guard}; # reduce memory usage, save a tree
317 336
318 # get handle 337 # get handle
319 $state{handle} = new AnyEvent::Handle 338 $state{handle} = new AnyEvent::Handle
… …
333 # (re-)configure handle 352 # (re-)configure handle
334 $state{handle}->timeout ($timeout); 353 $state{handle}->timeout ($timeout);
335 $state{handle}->on_error (sub { 354 $state{handle}->on_error (sub {
336 my $errno = "$!"; 355 my $errno = "$!";
337 %state = (); 356 %state = ();
338 $cb->(undef, { Status => 599, Reason => $errno }); 357 $cb->(undef, { Status => 599, Reason => $errno, URL => $url });
339 }); 358 });
340 $state{handle}->on_eof (sub { 359 $state{handle}->on_eof (sub {
341 %state = (); 360 %state = ();
342 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); 361 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
343 }); 362 });
344 363
345 # send request 364 # send request
346 $state{handle}->push_write ( 365 $state{handle}->push_write (
347 "$method $rpath HTTP/1.0\015\012" 366 "$method $rpath HTTP/1.0\015\012"
… …
352 371
353 %hdr = (); # reduce memory usage, save a kitten 372 %hdr = (); # reduce memory usage, save a kitten
354 373
355 # status line 374 # status line
356 $state{handle}->push_read (line => qr/\015?\012/, sub { 375 $state{handle}->push_read (line => qr/\015?\012/, sub {
357 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix 376 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
358 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" })); 377 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
359 378
360 my %hdr = ( # response headers 379 my %hdr = ( # response headers
361 HTTPVersion => "\x00$1", 380 HTTPVersion => "\x00$1",
362 Status => "\x00$2", 381 Status => "\x00$2",
363 Reason => "\x00$3", 382 Reason => "\x00$3",
383 URL => "\x00$url"
364 ); 384 );
365 385
366 # headers, could be optimized a bit 386 # headers, could be optimized a bit
367 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { 387 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
368 for ("$_[1]\012") { 388 for ("$_[1]\012") {
… …
375 ((?: [^\015\012]+ | \015?\012[\011\040] )*) 395 ((?: [^\015\012]+ | \015?\012[\011\040] )*)
376 \015?\012 396 \015?\012
377 /gxc; 397 /gxc;
378 398
379 /\G$/ 399 /\G$/
380 or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" })); 400 or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));
381 } 401 }
382 402
383 substr $_, 0, 1, "" 403 substr $_, 0, 1, ""
384 for values %hdr; 404 for values %hdr;
385 405
… …
394 my %kv = (value => $value, map { split /=/, $_, 2 } @arg); 414 my %kv = (value => $value, map { split /=/, $_, 2 } @arg);
395 415
396 my $cdom = (delete $kv{domain}) || $uhost; 416 my $cdom = (delete $kv{domain}) || $uhost;
397 my $cpath = (delete $kv{path}) || "/"; 417 my $cpath = (delete $kv{path}) || "/";
398 418
399 $cdom =~ s/^.?/./; # make sure it starts with a "." 419 $cdom =~ s/^\.?/./; # make sure it starts with a "."
400 420
401 next if $cdom =~ /\.$/; 421 next if $cdom =~ /\.$/;
402 422
403 # this is not rfc-like and not netscape-like. go figure. 423 # this is not rfc-like and not netscape-like. go figure.
404 my $ndots = $cdom =~ y/.//; 424 my $ndots = $cdom =~ y/.//;
… …
408 $arg{cookie_jar}{version} = 1; 428 $arg{cookie_jar}{version} = 1;
409 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; 429 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
410 } 430 }
411 } 431 }
412 432
413 if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {
414 # microsoft and other assholes don't give a shit for following standards, 433 # microsoft and other shitheads don't give a shit for following standards,
415 # try to support a common form of broken Location header. 434 # try to support some common forms of broken Location headers.
435 if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
436 $_[1]{location} =~ s/^\.\/+//;
437
416 $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%; 438 my $url = "$scheme://$uhost:$uport";
417 439
440 unless ($_[1]{location} =~ s/^\///) {
441 $url .= $upath;
442 $url =~ s/\/[^\/]*$//;
443 }
444
445 $_[1]{location} = "$url/$_[1]{location}";
446 }
447
448 if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
449 # apparently, mozilla et al. just change POST to GET here
450 # more research is needed before we do the same
418 http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); 451 http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
452 } elsif ($_[1]{Status} == 303 && $recurse) {
453 # even http/1.1 is unlear on how to mutate the method
454 $method = "GET" unless $method eq "HEAD";
455 http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
456 } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) {
457 http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
419 } else { 458 } else {
420 $cb->($_[0], $_[1]); 459 $cb->($_[0], $_[1]);
421 } 460 }
422 }; 461 };
423 462
… …
462 unshift @_, "HEAD"; 501 unshift @_, "HEAD";
463 &http_request 502 &http_request
464} 503}
465 504
466sub http_post($$@) { 505sub http_post($$@) {
506 my $url = shift;
467 unshift @_, "POST", "body"; 507 unshift @_, "POST", $url, "body";
468 &http_request 508 &http_request
469} 509}
470 510
471=back 511=back
472 512

Diff Legend

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