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 1.32 by root, Fri Oct 24 01:27:29 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 = '1.05';
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
216sub http_request($$$;@) { 242sub http_request($$@) {
217 my $cb = pop; 243 my $cb = pop;
218 my ($method, $url, %arg) = @_; 244 my ($method, $url, %arg) = @_;
219 245
220 my %hdr; 246 my %hdr;
221 247
… …
225 while (my ($k, $v) = each %$hdr) { 251 while (my ($k, $v) = each %$hdr) {
226 $hdr{lc $k} = $v; 252 $hdr{lc $k} = $v;
227 } 253 }
228 } 254 }
229 255
230 my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; 256 my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE;
231 257
232 return $cb->(undef, { Status => 599, Reason => "recursion limit reached" }) 258 return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url })
233 if $recurse < 0; 259 if $recurse < 0;
234 260
235 my $proxy = $arg{proxy} || $PROXY; 261 my $proxy = $arg{proxy} || $PROXY;
236 my $timeout = $arg{timeout} || $TIMEOUT; 262 my $timeout = $arg{timeout} || $TIMEOUT;
237 263
238 $hdr{"user-agent"} ||= $USERAGENT; 264 $hdr{"user-agent"} ||= $USERAGENT;
239 265
240 my ($scheme, $authority, $upath, $query, $fragment) = 266 my ($uscheme, $uauthority, $upath, $query, $fragment) =
241 $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; 267 $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|;
242 268
243 $scheme = lc $scheme; 269 $uscheme = lc $uscheme;
244 270
245 my $uport = $scheme eq "http" ? 80 271 my $uport = $uscheme eq "http" ? 80
246 : $scheme eq "https" ? 443 272 : $uscheme eq "https" ? 443
247 : 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 });
248 274
249 $hdr{referer} ||= "$scheme://$authority$upath"; # leave out fragment and query string, just a heuristic 275 $hdr{referer} ||= "$uscheme://$uauthority$upath"; # leave out fragment and query string, just a heuristic
250 276
251 $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x 277 $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
252 or return $cb->(undef, { Status => 599, Reason => "unparsable URL" }); 278 or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });
253 279
254 my $uhost = $1; 280 my $uhost = $1;
255 $uport = $2 if defined $2; 281 $uport = $2 if defined $2;
256 282
257 $uhost =~ s/^\[(.*)\]$/$1/; 283 $uhost =~ s/^\[(.*)\]$/$1/;
… …
259 285
260 $upath =~ s%^/?%/%; 286 $upath =~ s%^/?%/%;
261 287
262 # cookie processing 288 # cookie processing
263 if (my $jar = $arg{cookie_jar}) { 289 if (my $jar = $arg{cookie_jar}) {
264 %$jar = () if $jar->{version} < 1; 290 %$jar = () if $jar->{version} != 1;
265 291
266 my @cookie; 292 my @cookie;
267 293
268 while (my ($chost, $v) = each %$jar) { 294 while (my ($chost, $v) = each %$jar) {
295 if ($chost =~ /^\./) {
269 next unless $chost eq substr $uhost, -length $chost; 296 next unless $chost eq substr $uhost, -length $chost;
270 next unless $chost =~ /^\./; 297 } elsif ($chost =~ /\./) {
298 next unless $chost eq $uhost;
299 } else {
300 next;
301 }
271 302
272 while (my ($cpath, $v) = each %$v) { 303 while (my ($cpath, $v) = each %$v) {
273 next unless $cpath eq substr $upath, 0, length $cpath; 304 next unless $cpath eq substr $upath, 0, length $cpath;
274 305
275 while (my ($k, $v) = each %$v) { 306 while (my ($k, $v) = each %$v) {
276 next if $scheme ne "https" && exists $v->{secure}; 307 next if $uscheme ne "https" && exists $v->{secure};
308 my $value = $v->{value};
309 $value =~ s/([\\"])/\\$1/g;
277 push @cookie, "$k=$v->{value}"; 310 push @cookie, "$k=\"$value\"";
278 } 311 }
279 } 312 }
280 } 313 }
281 314
282 $hdr{cookie} = join "; ", @cookie 315 $hdr{cookie} = join "; ", @cookie
283 if @cookie; 316 if @cookie;
284 } 317 }
285 318
286 my ($rhost, $rport, $rpath); # request host, port, path 319 my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
287 320
288 if ($proxy) { 321 if ($proxy) {
289 ($rhost, $rport, $scheme) = @$proxy; 322 ($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url);
290 $rpath = $url; 323
324 # don't support https requests over https-proxy transport,
325 # can't be done with tls as spec'ed.
326 $rscheme = "http" if $uscheme eq "https" && $rscheme eq "https";
291 } else { 327 } else {
292 ($rhost, $rport, $rpath) = ($uhost, $uport, $upath); 328 ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
293 $hdr{host} = $uhost;
294 } 329 }
295 330
331 $hdr{host} = $uhost;
296 $hdr{"content-length"} = length $arg{body}; 332 $hdr{"content-length"} = length $arg{body};
297 333
298 my %state = (connect_guard => 1); 334 my %state = (connect_guard => 1);
299 335
300 _get_slot $uhost, sub { 336 _get_slot $uhost, sub {
… …
302 338
303 return unless $state{connect_guard}; 339 return unless $state{connect_guard};
304 340
305 $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { 341 $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub {
306 $state{fh} = shift 342 $state{fh} = shift
307 or return $cb->(undef, { Status => 599, Reason => "$!" }); 343 or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url });
308 344
309 delete $state{connect_guard}; # reduce memory usage, save a tree 345 delete $state{connect_guard}; # reduce memory usage, save a tree
310 346
311 # get handle 347 # get handle
312 $state{handle} = new AnyEvent::Handle 348 $state{handle} = new AnyEvent::Handle
313 fh => $state{fh}, 349 fh => $state{fh};
314 ($scheme eq "https" ? (tls => "connect") : ());
315 350
316 # limit the number of persistent connections 351 # limit the number of persistent connections
317 if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { 352 if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
318 ++$KA_COUNT{$_[1]}; 353 ++$KA_COUNT{$_[1]};
319 $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; 354 $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
… …
324 } 359 }
325 360
326 # (re-)configure handle 361 # (re-)configure handle
327 $state{handle}->timeout ($timeout); 362 $state{handle}->timeout ($timeout);
328 $state{handle}->on_error (sub { 363 $state{handle}->on_error (sub {
364 my $errno = "$!";
329 %state = (); 365 %state = ();
330 $cb->(undef, { Status => 599, Reason => "$!" }); 366 $cb->(undef, { Status => 599, Reason => $errno, URL => $url });
331 }); 367 });
332 $state{handle}->on_eof (sub { 368 $state{handle}->on_eof (sub {
333 %state = (); 369 %state = ();
334 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file" }); 370 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
335 }); 371 });
336 372
373 $state{handle}->starttls ("connect") if $rscheme eq "https";
374
375 # handle actual, non-tunneled, request
376 my $handle_actual_request = sub {
377# $state{handle}->starttls ("connect") if $uscheme eq "https";
378
337 # send request 379 # send request
338 $state{handle}->push_write ( 380 $state{handle}->push_write (
339 "$method $rpath HTTP/1.0\015\012" 381 "$method $rpath HTTP/1.0\015\012"
340 . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) 382 . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)
341 . "\015\012" 383 . "\015\012"
342 . (delete $arg{body}) 384 . (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 ); 385 );
357 386
387 %hdr = (); # reduce memory usage, save a kitten
388
389 # status line
390 $state{handle}->push_read (line => qr/\015?\012/, sub {
391 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
392 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid server response ($_[1])", URL => $url }));
393
394 my %hdr = ( # response headers
395 HTTPVersion => ",$1",
396 Status => ",$2",
397 Reason => ",$3",
398 URL => ",$url"
399 );
400
358 # headers, could be optimized a bit 401 # headers, could be optimized a bit
359 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { 402 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
360 for ("$_[1]\012") { 403 for ("$_[1]\012") {
404 y/\015//d; # weed out any \015, as they show up in the weirdest of places.
405
361 # we support spaces in field names, as lotus domino 406 # we support spaces in field names, as lotus domino
362 # creates them. 407 # creates them (actually spaces around seperators
408 # are strictly allowed in http, they are a security issue).
363 $hdr{lc $1} .= "\x00$2" 409 $hdr{lc $1} .= ",$2"
364 while /\G 410 while /\G
365 ([^:\000-\037]+): 411 ([^:\000-\037]+):
366 [\011\040]* 412 [\011\040]*
367 ((?: [^\015\012]+ | \015?\012[\011\040] )*) 413 ((?: [^\012]+ | \012[\011\040] )*)
368 \015?\012 414 \012
369 /gxc; 415 /gxc;
370 416
371 /\G$/ 417 /\G$/
372 or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers" })); 418 or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));
373 } 419 }
374 420
375 substr $_, 0, 1, "" 421 substr $_, 0, 1, ""
376 for values %hdr; 422 for values %hdr;
377 423
378 my $finish = sub { 424 my $finish = sub {
425 # TODO: use destroy method, when/if available
426 #$state{handle}->destroy;
427 $state{handle}->on_eof (undef);
428 $state{handle}->on_error (undef);
379 %state = (); 429 %state = ();
380 430
381 # set-cookie processing 431 # set-cookie processing
382 if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { 432 if ($arg{cookie_jar}) {
383 for (split /\x00/, $hdr{"set-cookie"}) { 433 for ($hdr{"set-cookie"}) {
384 my ($cookie, @arg) = split /;\s*/; 434 # parse NAME=VALUE
385 my ($name, $value) = split /=/, $cookie, 2; 435 my @kv;
386 my %kv = (value => $value, map { split /=/, $_, 2 } @arg); 436
387 437 while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) {
388 my $cdom = (delete $kv{domain}) || $uhost; 438 my $name = $1;
439 my $value = $3;
440
441 unless ($value) {
442 $value = $2;
443 $value =~ s/\\(.)/$1/gs;
444 }
445
446 push @kv, $name => $value;
447
448 last unless /\G\s*;/gc;
449 }
450
451 last unless @kv;
452
453 my $name = shift @kv;
454 my %kv = (value => shift @kv, @kv);
455
456 my $cdom;
389 my $cpath = (delete $kv{path}) || "/"; 457 my $cpath = (delete $kv{path}) || "/";
390 458
459 if (exists $kv{domain}) {
460 $cdom = delete $kv{domain};
461
391 $cdom =~ s/^.?/./; # make sure it starts with a "." 462 $cdom =~ s/^\.?/./; # make sure it starts with a "."
392 463
393 next if $cdom =~ /\.$/; 464 next if $cdom =~ /\.$/;
394 465
395 # this is not rfc-like and not netscape-like. go figure. 466 # this is not rfc-like and not netscape-like. go figure.
396 my $ndots = $cdom =~ y/.//; 467 my $ndots = $cdom =~ y/.//;
397 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); 468 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
398 469 } else {
470 $cdom = $uhost;
471 }
472
399 # store it 473 # store it
400 $arg{cookie_jar}{version} = 1; 474 $arg{cookie_jar}{version} = 1;
401 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; 475 $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv;
476
477 redo if /\G\s*,/gc;
478 }
479 }
480
481 # microsoft and other shitheads don't give a shit for following standards,
482 # try to support some common forms of broken Location headers.
483 if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) {
484 $_[1]{location} =~ s/^\.\/+//;
485
486 my $url = "$rscheme://$uhost:$uport";
487
488 unless ($_[1]{location} =~ s/^\///) {
489 $url .= $upath;
490 $url =~ s/\/[^\/]*$//;
491 }
492
493 $_[1]{location} = "$url/$_[1]{location}";
494 }
495
496 if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
497 # apparently, mozilla et al. just change POST to GET here
498 # more research is needed before we do the same
499 http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
500 } elsif ($_[1]{Status} == 303 && $recurse) {
501 # even http/1.1 is unclear on how to mutate the method
502 $method = "GET" unless $method eq "HEAD";
503 http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
504 } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) {
505 http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
506 } else {
507 $cb->($_[0], $_[1]);
508 }
509 };
510
511 if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") {
512 $finish->(undef, \%hdr);
513 } else {
514 if (exists $hdr{"content-length"}) {
515 $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub {
516 # could cache persistent connection now
517 if ($hdr{connection} =~ /\bkeep-alive\b/i) {
518 # but we don't, due to misdesigns, this is annoyingly complex
519 };
520
521 $finish->($_[1], \%hdr);
522 });
523 } else {
524 # too bad, need to read until we get an error or EOF,
525 # no way to detect winged data.
526 $_[0]->on_error (sub {
527 $finish->($_[0]{rbuf}, \%hdr);
528 });
529 $_[0]->on_eof (undef);
530 $_[0]->on_read (sub { });
402 } 531 }
403 } 532 }
404
405 if ($_[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], $_[1]);
413 }
414 }; 533 });
534 });
535 };
415 536
416 if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { 537 # now handle proxy-CONNECT method
417 $finish->(undef, \%hdr); 538 if ($proxy && $uscheme eq "https") {
539 # oh dear, we have to wrap it into a connect request
540
541 # maybe re-use $uauthority with patched port?
542 $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012");
543 $state{handle}->push_read (line => qr/\015?\012\015?\012/, sub {
544 $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix
545 or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url }));
546
547 if ($2 == 200) {
548 $rpath = $upath;
549 &$handle_actual_request;
418 } else { 550 } else {
419 if (exists $hdr{"content-length"}) { 551 %state = ();
420 $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { 552 $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 $_[0]->on_read (sub { });
436 }
437 } 553 }
438 }); 554 });
555 } else {
556 &$handle_actual_request;
439 }); 557 }
558
440 }, sub { 559 }, sub {
441 $timeout 560 $timeout
442 }; 561 };
443 }; 562 };
444 563
445 defined wantarray && AnyEvent::Util::guard { %state = () } 564 defined wantarray && AnyEvent::Util::guard { %state = () }
446} 565}
447 566
448sub http_get($$;@) { 567sub http_get($@) {
449 unshift @_, "GET"; 568 unshift @_, "GET";
450 &http_request 569 &http_request
451} 570}
452 571
453sub http_head($$;@) { 572sub http_head($@) {
454 unshift @_, "HEAD"; 573 unshift @_, "HEAD";
455 &http_request 574 &http_request
456} 575}
457 576
458sub http_post($$$;@) { 577sub http_post($$@) {
578 my $url = shift;
459 unshift @_, "POST", "body"; 579 unshift @_, "POST", $url, "body";
460 &http_request 580 &http_request
461} 581}
462 582
463=back 583=back
464 584
… …
489=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT 609=item $AnyEvent::HTTP::PERSISTENT_TIMEOUT
490 610
491The maximum time to cache a persistent connection, in seconds (default: 2). 611The maximum time to cache a persistent connection, in seconds (default: 2).
492 612
493Not implemented currently. 613Not implemented currently.
614
615=item $AnyEvent::HTTP::ACTIVE
616
617The number of active connections. This is not the number of currently
618running requests, but the number of currently open and non-idle TCP
619connections. This number of can be useful for load-leveling.
494 620
495=back 621=back
496 622
497=cut 623=cut
498 624
… …
507 633
508L<AnyEvent>. 634L<AnyEvent>.
509 635
510=head1 AUTHOR 636=head1 AUTHOR
511 637
512 Marc Lehmann <schmorp@schmorp.de> 638 Marc Lehmann <schmorp@schmorp.de>
513 http://home.schmorp.de/ 639 http://home.schmorp.de/
514 640
515=cut 641=cut
516 642
5171 6431
518 644

Diff Legend

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