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 1.13 by root, Thu Jun 5 16:43:45 2008 UTC vs.
Revision 1.35 by root, Thu Oct 30 03:47:01 2008 UTC

… …
3AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client 3AnyEvent::HTTP - simple but non-blocking HTTP/HTTPS client
4 4
5=head1 SYNOPSIS 5=head1 SYNOPSIS
6 6
7 use AnyEvent::HTTP; 7 use AnyEvent::HTTP;
8
9 http_get "http://www.nethype.de/", sub { print $_[1] };
10
11 # ... do something else here
8 12
9=head1 DESCRIPTION 13=head1 DESCRIPTION
10 14
11This module is an L<AnyEvent> user, you need to make sure that you use and 15This module is an L<AnyEvent> user, you need to make sure that you use and
12run a supported event loop. 16run a supported event loop.
… …
44use AnyEvent::Socket (); 48use AnyEvent::Socket ();
45use AnyEvent::Handle (); 49use AnyEvent::Handle ();
46 50
47use base Exporter::; 51use base Exporter::;
48 52
49our $VERSION = '1.0'; 53our $VERSION = '1.1';
50 54
51our @EXPORT = qw(http_get http_request); 55our @EXPORT = qw(http_get http_post http_head http_request);
52 56
53our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; 57our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)";
54our $MAX_RECURSE = 10; 58our $MAX_RECURSE = 10;
55our $MAX_PERSISTENT = 8; 59our $MAX_PERSISTENT = 8;
56our $PERSISTENT_TIMEOUT = 2; 60our $PERSISTENT_TIMEOUT = 2;
… …
59# changing these is evil 63# changing these is evil
60our $MAX_PERSISTENT_PER_HOST = 2; 64our $MAX_PERSISTENT_PER_HOST = 2;
61our $MAX_PER_HOST = 4; 65our $MAX_PER_HOST = 4;
62 66
63our $PROXY; 67our $PROXY;
68our $ACTIVE = 0;
64 69
65my %KA_COUNT; # number of open keep-alive connections per host 70my %KA_COUNT; # number of open keep-alive connections per host
66my %CO_SLOT; # number of open connections, and wait queue, per host 71my %CO_SLOT; # number of open connections, and wait queue, per host
67 72
68=item http_get $url, key => value..., $cb->($data, $headers) 73=item http_get $url, key => value..., $cb->($data, $headers)
69 74
70Executes 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
71additional parameters. 76additional parameters and the return value.
72 77
73=item http_head $url, key => value..., $cb->($data, $headers) 78=item http_head $url, key => value..., $cb->($data, $headers)
74 79
75Executes an HTTP-HEAD request. See the http_request function for details on 80Executes an HTTP-HEAD request. See the http_request function for details
76additional parameters. 81on additional parameters and the return value.
77 82
78=item http_post $url, $body, key => value..., $cb->($data, $headers) 83=item http_post $url, $body, key => value..., $cb->($data, $headers)
79 84
80Executes an HTTP-POST request with a request body of C<$bod>. See the 85Executes an HTTP-POST request with a request body of C<$body>. See the
81http_request function for details on additional parameters. 86http_request function for details on additional parameters and the return
87value.
82 88
83=item http_request $method => $url, key => value..., $cb->($data, $headers) 89=item http_request $method => $url, key => value..., $cb->($data, $headers)
84 90
85Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL 91Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL
86must be an absolute http or https URL. 92must be an absolute http or https URL.
93
94When called in void context, nothing is returned. In other contexts,
95C<http_request> returns a "cancellation guard" - you have to keep the
96object at least alive until the callback get called. If the object gets
97destroyed before the callbakc is called, the request will be cancelled.
87 98
88The callback will be called with the response data as first argument 99The callback will be called with the response data as first argument
89(or C<undef> if it wasn't available due to errors), and a hash-ref with 100(or C<undef> if it wasn't available due to errors), and a hash-ref with
90response headers as second argument. 101response headers as second argument.
91 102
92All the headers in that hash are lowercased. In addition to the response 103All the headers in that hash are lowercased. In addition to the response
93headers, the three "pseudo-headers" C<HTTPVersion>, C<Status> and 104headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>
94C<Reason> contain the three parts of the HTTP Status-Line of the same 105contain the three parts of the HTTP Status-Line of the same name. The
106pseudo-header C<URL> contains the original URL (which can differ from the
107requested URL when following redirects).
108
95name. If the server sends a header multiple lines, then their contents 109If the server sends a header multiple times, then their contents will be
96will be joined together with C<\x00>. 110joined together with a comma (C<,>), as per the HTTP spec.
97 111
98If an internal error occurs, such as not being able to resolve a hostname, 112If an internal error occurs, such as not being able to resolve a hostname,
99then C<$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>
100and the C<Reason> pseudo-header will contain an error message. 114and the C<Reason> pseudo-header will contain an error message.
101 115
… …
181 use Data::Dumper; 195 use Data::Dumper;
182 print Dumper $hdr; 196 print Dumper $hdr;
183 } 197 }
184 ; 198 ;
185 199
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 $request;
209
186=cut 210=cut
187 211
188sub _slot_schedule; 212sub _slot_schedule;
189sub _slot_schedule($) { 213sub _slot_schedule($) {
190 my $host = shift; 214 my $host = shift;
191 215
192 while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) { 216 while ($CO_SLOT{$host}[0] < $MAX_PER_HOST) {
193 if (my $cb = shift @{ $CO_SLOT{$host}[1] }) { 217 if (my $cb = shift @{ $CO_SLOT{$host}[1] }) {
194 # somebody wants that slot 218 # somebody wants that slot
195 ++$CO_SLOT{$host}[0]; 219 ++$CO_SLOT{$host}[0];
220 ++$ACTIVE;
196 221
197 $cb->(AnyEvent::Util::guard { 222 $cb->(AnyEvent::Util::guard {
223 --$ACTIVE;
198 --$CO_SLOT{$host}[0]; 224 --$CO_SLOT{$host}[0];
199 _slot_schedule $host; 225 _slot_schedule $host;
200 }); 226 });
201 } else { 227 } else {
202 # nobody wants the slot, maybe we can forget about it 228 # nobody wants the slot, maybe we can forget about it
… …
211 push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; 237 push @{ $CO_SLOT{$_[0]}[1] }, $_[1];
212 238
213 _slot_schedule $_[0]; 239 _slot_schedule $_[0];
214} 240}
215 241
242our $qr_nl = qr<\015?\012>;
243our $qr_nlnl = qr<\015?\012\015?\012>;
244
216sub http_request($$$;@) { 245sub http_request($$@) {
217 my $cb = pop; 246 my $cb = pop;
218 my ($method, $url, %arg) = @_; 247 my ($method, $url, %arg) = @_;
219 248
220 my %hdr; 249 my %hdr;
221 250
… …
225 while (my ($k, $v) = each %$hdr) { 254 while (my ($k, $v) = each %$hdr) {
226 $hdr{lc $k} = $v; 255 $hdr{lc $k} = $v;
227 } 256 }
228 } 257 }
229 258
230 my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; 259 my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
231 260
232 return $cb->(undef, { Status => 599, Reason => "recursion limit reached" }) 261 return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })
233 if $recurse < 0; 262 if $recurse < 0;
234 263
235 my $proxy = $arg{proxy} || $PROXY; 264 my $proxy = $arg{proxy} || $PROXY;
236 my $timeout = $arg{timeout} || $TIMEOUT; 265 my $timeout = $arg{timeout} || $TIMEOUT;
237 266
238 $hdr{"user-agent"} ||= $USERAGENT; 267 $hdr{"user-agent"} ||= $USERAGENT;
239 268
240 my ($scheme, $authority, $upath, $query, $fragment) = 269 my ($uscheme, $uauthority, $upath, $query, $fragment) =
241 $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; 270 $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|;
242 271
243 $scheme = lc $scheme; 272 $uscheme = lc $uscheme;
244 273
245 my $uport = $scheme eq "http" ? 80 274 my $uport = $uscheme eq "http" ? 80
246 : $scheme eq "https" ? 443 275 : $uscheme eq "https" ? 443
247 : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported" }); 276 : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });
248 277
249 $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic 278 $hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
250 279
251 $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x 280 $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
252 or return $cb->(undef, { Status => 599, Reason => "unparsable URL" }); 281 or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });
253 282
254 my $uhost = $1; 283 my $uhost = $1;
255 $uport = $2 if defined $2; 284 $uport = $2 if defined $2;
256 285
257 $uhost =~ s/^\[(.*)\]$/$1/; 286 $uhost =~ s/^\[(.*)\]$/$1/;
… …
259 288
260 $upath =~ s%^/?%/%; 289 $upath =~ s%^/?%/%;
261 290
262 # cookie processing 291 # cookie processing
263 if (my $jar = $arg{cookie_jar}) { 292 if (my $jar = $arg{cookie_jar}) {
264 %$jar = () if $jar->{version} < 1; 293 %$jar = () if $jar->{version} != 1;
265 294
266 my @cookie; 295 my @cookie;
267 296
268 while (my ($chost, $v) = each %$jar) { 297 while (my ($chost, $v) = each %$jar) {
298 if ($chost =~ /^\./) {
269 next unless $chost eq substr $uhost, -length $chost; 299 next unless $chost eq substr $uhost, -length $chost;
270 next unless $chost =~ /^\./; 300 } elsif ($chost =~ /\./) {
301 next unless $chost eq $uhost;
302 } else {
303 next;
304 }
271 305
272 while (my ($cpath, $v) = each %$v) { 306 while (my ($cpath, $v) = each %$v) {
273 next unless $cpath eq substr $upath, 0, length $cpath; 307 next unless $cpath eq substr $upath, 0, length $cpath;
274 308
275 while (my ($k, $v) = each %$v) { 309 while (my ($k, $v) = each %$v) {
276 next if $scheme ne "https" && exists $v->{secure}; 310 next if $uscheme ne "https" && exists $v->{secure};
311 my $value = $v->{value};
312 $value =~ s/([\\"])/\\$1/g;
277 push @cookie, "$k=$v->{value}"; 313 push @cookie, "$k=\"$value\"";
278 } 314 }
279 } 315 }
280 } 316 }
281 317
282 $hdr{cookie} = join "; ", @cookie 318 $hdr{cookie} = join "; ", @cookie
283 if @cookie; 319 if @cookie;
284 } 320 }
285 321
286 my ($rhost, $rport, $rpath); # request host, port, path 322 my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
287 323
288 if ($proxy) { 324 if ($proxy) {
289 ($rhost, $rport, $scheme) = @$proxy; 325 ($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url);
290 $rpath = $url; 326
327 # don't support https requests over https-proxy transport,
328 # can't be done with tls as spec'ed.
329 $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
291 } else { 330 } else {
292 ($rhost, $rport, $rpath) = ($uhost, $uport, $upath); 331 ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
293 $hdr{host} = $uhost;
294 } 332 }
295 333
334 $hdr{host} = $uhost;
296 $hdr{"content-length"} = length $arg{body}; 335 $hdr{"content-length"} = length $arg{body};
297 336
298 my %state = (connect_guard => 1); 337 my %state = (connect_guard => 1);
299 338
300 _get_slot $uhost, sub { 339 _get_slot $uhost, sub {
… …
302 341
303 return unless $state{connect_guard}; 342 return unless $state{connect_guard};
304 343
305 $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { 344 $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
306 $state{fh} = shift 345 $state{fh} = shift
307 or return $cb->(undef, { Status => 599, Reason => "$!" }); 346 or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });
347 pop; # free memory, save a tree
308 348
309 delete $state{connect_guard}; # reduce memory usage, save a tree 349 return unless delete $state{connect_guard};
310 350
311 # get handle 351 # get handle
312 $state{handle} = new AnyEvent::Handle 352 $state{handle} = new AnyEvent::Handle
313 fh => $state{fh}, 353 fh => $state{fh},
314 ($scheme eq "https" ? (tls => "connect") : ()); 354 timeout => $timeout;
315 355
316 # limit the number of persistent connections 356 # limit the number of persistent connections
357 # keepalive not yet supported
317 if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { 358 if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
318 ++$KA_COUNT{$_[1]}; 359 ++$KA_COUNT{$_[1]};
319 $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; 360 $state{handle}{ka_count_guard} = AnyEvent::Util::guard {
361 --$KA_COUNT{$_[1]}
362 };
320 $hdr{connection} = "keep-alive"; 363 $hdr{connection} = "keep-alive";
321 delete $hdr{connection}; # keep-alive not yet supported
322 } else { 364 } else {
323 delete $hdr{connection}; 365 delete $hdr{connection};
324 } 366 }
325 367
326 # (re-)configure handle 368 # (re-)configure handle
327 $state{handle}->timeout ($timeout);
328 $state{handle}->on_error (sub { 369 $state{handle}->on_error (sub {
370 my $errno = "$!";
329 %state = (); 371 %state = ();
330 $cb->(undef, { Status => 599, Reason => "$!" }); 372 $cb->(undef, { Status => 599, Reason => $errno, URL => $url });
331 }); 373 });
332 $state{handle}->on_eof (sub { 374 $state{handle}->on_eof (sub {
333 %state = (); 375 %state = ();
334 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); 376 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
335 }); 377 });
336 378
379 $state{handle}->starttls ("connect") if $rscheme eq "https";
380
381 # handle actual, non-tunneled, request
382 my $handle_actual_request = sub {
383 $state{handle}->starttls ("connect") if $uscheme eq "https" && !exists $state{handle}{tls};
384
337 # send request 385 # send request
338 $state{handle}->push_write ( 386 $state{handle}->push_write (
339 "$method $rpath HTTP/1.0\015\012" 387 "$method $rpath HTTP/1.0\015\012"
340 . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) 388 . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)
341 . "\015\012" 389 . "\015\012"
342 . (delete $arg{body}) 390 . (delete $arg{body})
343 );
344
345 %hdr = (); # reduce memory usage, save a kitten
346
347 # status line
348 $state{handle}->push_read (line => qr/\015?\012/, sub {
349 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) \s+ ([^\015\012]+)/ix
350 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])" }));
351
352 my %hdr = ( # response headers
353 HTTPVersion => "\x00$1",
354 Status => "\x00$2",
355 Reason => "\x00$3",
356 ); 391 );
357 392
393 %hdr = (); # reduce memory usage, save a kitten
394
395 # status line
396 $state{handle}->push_read (line => $qr_nl, sub {
397 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
398 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
399
400 my %hdr = ( # response headers
401 HTTPVersion => ",$1",
402 Status => ",$2",
403 Reason => ",$3",
404 URL => ",$url"
405 );
406
358 # headers, could be optimized a bit 407 # headers, could be optimized a bit
359 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { 408 $state{handle}->unshift_read (line => $qr_nlnl, sub {
360 for ("$_[1]\012") { 409 for ("$_[1]\012") {
410 y/\015//d; # weed out any \015, as they show up in the weirdest of places.
411
361 # we support spaces in field names, as lotus domino 412 # we support spaces in field names, as lotus domino
362 # creates them. 413 # creates them (actually spaces around seperators
414 # are strictly allowed in http, they are a security issue).
363 $hdr{lc $1} .= "\x00$2" 415 $hdr{lc $1} .= ",$2"
364 while /\G 416 while /\G
365 ([^:\000-\037]+): 417 ([^:\000-\037]+):
366 [\011\040]* 418 [\011\040]*
367 ((?: [^\015\012]+ | \015?\012[\011\040] )*) 419 ((?: [^\012]+ | \012[\011\040] )*)
368 \015?\012 420 \012
369 /gxc; 421 /gxc;
370 422
371 /\G$/ 423 /\G$/
372 or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" })); 424 or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));
373 } 425 }
374 426
375 substr $_, 0, 1, "" 427 substr $_, 0, 1, ""
376 for values %hdr; 428 for values %hdr;
377 429
378 my $finish = sub { 430 my $finish = sub {
431 $state{handle}->destroy;
379 %state = (); 432 %state = ();
380 433
381 # set-cookie processing 434 # set-cookie processing
382 if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { 435 if ($arg{cookie_jar}) {
383 for (split /\x00/, $hdr{"set-cookie"}) { 436 for ($hdr{"set-cookie"}) {
384 my ($cookie, @arg) = split /;\s*/; 437 # parse NAME=VALUE
385 my ($name, $value) = split /=/, $cookie, 2; 438 my @kv;
386 my %kv = (value => $value, map { split /=/, $_, 2 } @arg); 439
387 440 while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) {
388 my $cdom = (delete $kv{domain}) || $uhost; 441 my $name = $1;
442 my $value = $3;
443
444 unless ($value) {
445 $value = $2;
446 $value =~ s/\\(.)/$1/gs;
447 }
448
449 push @kv, $name => $value;
450
451 last unless /\G\s*;/gc;
452 }
453
454 last unless @kv;
455
456 my $name = shift @kv;
457 my %kv = (value => shift @kv, @kv);
458
459 my $cdom;
389 my $cpath = (delete $kv{path}) || "/"; 460 my $cpath = (delete $kv{path}) || "/";
390 461
462 if (exists $kv{domain}) {
463 $cdom = delete $kv{domain};
464
391 $cdom =~ s/^.?/./; # make sure it starts with a "." 465 $cdom =~ s/^\.?/./; # make sure it starts with a "."
392 466
393 next if $cdom =~ /\.$/; 467 next if $cdom =~ /\.$/;
394 468
395 # this is not rfc-like and not netscape-like. go figure. 469 # this is not rfc-like and not netscape-like. go figure.
396 my $ndots = $cdom =~ y/.//; 470 my $ndots = $cdom =~ y/.//;
397 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); 471 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
398 472 } else {
473 $cdom = $uhost;
474 }
475
399 # store it 476 # store it
400 $arg{cookie_jar}{version} = 1; 477 $arg{cookie_jar}{version} = 1;
401 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; 478 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
479
480 redo if /\G\s*,/gc;
481 }
482 }
483
484 # microsoft and other shitheads don't give a shit for following standards,
485 # try to support some common forms of broken Location headers.
486 if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
487 $_[1]{location} =~ s/^\.\/+//;
488
489 my $url = "$rscheme://$uhost:$uport";
490
491 unless ($_[1]{location} =~ s/^\///) {
492 $url .= $upath;
493 $url =~ s/\/[^\/]*$//;
494 }
495
496 $_[1]{location} = "$url/$_[1]{location}";
497 }
498
499 if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
500 # apparently, mozilla et al. just change POST to GET here
501 # more research is needed before we do the same
502 http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
503 } elsif ($_[1]{Status} == 303 && $recurse) {
504 # even http/1.1 is unclear on how to mutate the method
505 $method = "GET" unless $method eq "HEAD";
506 http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
507 } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) {
508 http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
509 } else {
510 $cb->($_[0], $_[1]);
511 }
512 };
513
514 if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") {
515 $finish->(undef, \%hdr);
516 } else {
517 if (exists $hdr{"content-length"}) {
518 $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
519 # could cache persistent connection now
520 if ($hdr{connection} =~ /\bkeep-alive\b/i) {
521 # but we don't, due to misdesigns, this is annoyingly complex
522 };
523
524 $finish->($_[1], \%hdr);
525 });
526 } else {
527 # too bad, need to read until we get an error or EOF,
528 # no way to detect winged data.
529 $_[0]->on_error (sub {
530 $finish->($_[0]{rbuf}, \%hdr);
531 });
532 $_[0]->on_eof (undef);
533 $_[0]->on_read (sub { });
402 } 534 }
403 } 535 }
404
405 if ($_[1]{Status} =~ /^30[12]$/ && $recurse) {
406 # microsoft and other assholes don't give a shit for following standards,
407 # try to support a common form of broken Location header.
408 $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
409
410 http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
411 } else {
412 $cb->($_[0], $_[1]);
413 }
414 }; 536 });
537 });
538 };
415 539
416 if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { 540 # now handle proxy-CONNECT method
417 $finish->(undef, \%hdr); 541 if ($proxy && $uscheme eq "https") {
542 # oh dear, we have to wrap it into a connect request
543
544 # maybe re-use $uauthority with patched port?
545 $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
546 $state{handle}->push_read (line => $qr_nlnl, sub {
547 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
548 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url }));
549
550 if ($2 == 200) {
551 $rpath = $upath;
552 &$handle_actual_request;
418 } else { 553 } else {
419 if (exists $hdr{"content-length"}) { 554 %state = ();
420 $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { 555 $cb->(undef, { Status => $2, Reason => $3, URL => $url });
421 # could cache persistent connection now
422 if ($hdr{connection} =~ /\bkeep-alive\b/i) {
423 # but we don't, due to misdesigns, this is annoyingly complex
424 };
425
426 $finish->($_[1], \%hdr);
427 });
428 } else {
429 # too bad, need to read until we get an error or EOF,
430 # no way to detect winged data.
431 $_[0]->on_error (sub {
432 $finish->($_[0]{rbuf}, \%hdr);
433 });
434 $_[0]->on_eof (undef);
435 $_[0]->on_read (sub { });
436 }
437 } 556 }
438 }); 557 });
558 } else {
559 &$handle_actual_request;
439 }); 560 }
561
440 }, sub { 562 }, sub {
441 $timeout 563 $timeout
442 }; 564 };
443 }; 565 };
444 566
445 defined wantarray && AnyEvent::Util::guard { %state = () } 567 defined wantarray && AnyEvent::Util::guard { %state = () }
446} 568}
447 569
448sub http_get($$;@) { 570sub http_get($@) {
449 unshift @_, "GET"; 571 unshift @_, "GET";
450 &http_request 572 &http_request
451} 573}
452 574
453sub http_head($$;@) { 575sub http_head($@) {
454 unshift @_, "HEAD"; 576 unshift @_, "HEAD";
455 &http_request 577 &http_request
456} 578}
457 579
458sub http_post($$$;@) { 580sub http_post($$@) {
581 my $url = shift;
459 unshift @_, "POST", "body"; 582 unshift @_, "POST", $url, "body";
460 &http_request 583 &http_request
461} 584}
462 585
463=back 586=back
464 587
… …
489=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT 612=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
490 613
491The maximum time to cache a persistent connection, in seconds (default: 2). 614The maximum time to cache a persistent connection, in seconds (default: 2).
492 615
493Not implemented currently. 616Not implemented currently.
617
618=item $AnyEvent::HTTP::ACTIVE
619
620The number of active connections. This is not the number of currently
621running requests, but the number of currently open and non-idle TCP
622connections. This number of can be useful for load-leveling.
494 623
495=back 624=back
496 625
497=cut 626=cut
498 627
… …
507 636
508L<AnyEvent>. 637L<AnyEvent>.
509 638
510=head1 AUTHOR 639=head1 AUTHOR
511 640
512 Marc Lehmann <schmorp@schmorp.de> 641 Marc Lehmann <schmorp@schmorp.de>
513 http://home.schmorp.de/ 642 http://home.schmorp.de/
514 643
515=cut 644=cut
516 645
5171 6461
518 647

Diff Legend

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