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 1.23 by root, Wed Jul 2 01:23:41 2008 UTC vs.
Revision 1.33 by root, Mon Oct 27 11:09:54 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 = '1.03'; 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<$method> (e.g. C<GET>, C<POST>). The URL
91must be an absolute http or https URL. 92must be an absolute http or https URL.
93
94When called in void context, nothing is returned. In other contexts,
95C<http_request> returns a "cancellation guard" - you have to keep the
96object at least alive until the callback get called. If the object gets
97destroyed before the callbakc is called, the request will be cancelled.
92 98
93The callback will be called with the response data as first argument 99The callback will be called with the response data as first argument
94(or C<undef> if it wasn't available due to errors), and a hash-ref with 100(or C<undef> if it wasn't available due to errors), and a hash-ref with
95response headers as second argument. 101response headers as second argument.
96 102
… …
98headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> 104headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason>
99contain the three parts of the HTTP Status-Line of the same name. The 105contain the three parts of the HTTP Status-Line of the same name. The
100pseudo-header C<URL> contains the original URL (which can differ from the 106pseudo-header C<URL> contains the original URL (which can differ from the
101requested URL when following redirects). 107requested URL when following redirects).
102 108
103If the server sends a header multiple lines, then their contents will be 109If the server sends a header multiple times, then their contents will be
104joined together with C<\x00>. 110joined together with a comma (C<,>), as per the HTTP spec.
105 111
106If an internal error occurs, such as not being able to resolve a hostname, 112If an internal error occurs, such as not being able to resolve a hostname,
107then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> 113then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599>
108and the C<Reason> pseudo-header will contain an error message. 114and the C<Reason> pseudo-header will contain an error message.
109 115
… …
188 my ($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($) {
… …
245 my $proxy = $arg{proxy} || $PROXY; 261 my $proxy = $arg{proxy} || $PROXY;
246 my $timeout = $arg{timeout} || $TIMEOUT; 262 my $timeout = $arg{timeout} || $TIMEOUT;
247 263
248 $hdr{"user-agent"} ||= $USERAGENT; 264 $hdr{"user-agent"} ||= $USERAGENT;
249 265
250 my ($scheme, $authority, $upath, $query, $fragment) = 266 my ($uscheme, $uauthority, $upath, $query, $fragment) =
251 $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; 267 $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|;
252 268
253 $scheme = lc $scheme; 269 $uscheme = lc $uscheme;
254 270
255 my $uport = $scheme eq "http" ? 80 271 my $uport = $uscheme eq "http" ? 80
256 : $scheme eq "https" ? 443 272 : $uscheme eq "https" ? 443
257 : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); 273 : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url });
258 274
259 $hdr{referer} ||= "$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
260 276
261 $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x 277 $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x
262 or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); 278 or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url });
263 279
264 my $uhost = $1; 280 my $uhost = $1;
265 $uport = $2 if defined $2; 281 $uport = $2 if defined $2;
266 282
… …
269 285
270 $upath =~ s%^/?%/%; 286 $upath =~ s%^/?%/%;
271 287
272 # cookie processing 288 # cookie processing
273 if (my $jar = $arg{cookie_jar}) { 289 if (my $jar = $arg{cookie_jar}) {
274 %$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) {
286 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;
287 push @cookie, "$k=$v->{value}"; 310 push @cookie, "$k=\"$value\"";
288 } 311 }
289 } 312 }
290 } 313 }
291 314
292 $hdr{cookie} = join "; ", @cookie 315 $hdr{cookie} = join "; ", @cookie
293 if @cookie; 316 if @cookie;
294 } 317 }
295 318
296 my ($rhost, $rport, $rpath); # request host, port, path 319 my ($rhost, $rport, $rscheme, $rpath); # request host, port, path
297 320
298 if ($proxy) { 321 if ($proxy) {
299 ($rhost, $rport, $scheme) = @$proxy; 322 ($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url);
300 $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" && $rscheme eq "https";
301 } else { 327 } else {
302 ($rhost, $rport, $rpath) = ($uhost, $uport, $upath); 328 ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath);
303 $hdr{host} = $uhost;
304 } 329 }
305 330
331 $hdr{host} = $uhost;
306 $hdr{"content-length"} = length $arg{body}; 332 $hdr{"content-length"} = length $arg{body};
307 333
308 my %state = (connect_guard => 1); 334 my %state = (connect_guard => 1);
309 335
310 _get_slot $uhost, sub { 336 _get_slot $uhost, sub {
… …
318 344
319 delete $state{connect_guard}; # reduce memory usage, save a tree 345 delete $state{connect_guard}; # reduce memory usage, save a tree
320 346
321 # get handle 347 # get handle
322 $state{handle} = new AnyEvent::Handle 348 $state{handle} = new AnyEvent::Handle
323 fh => $state{fh}, 349 fh => $state{fh};
324 ($scheme eq "https" ? (tls => "connect") : ());
325 350
326 # limit the number of persistent connections 351 # limit the number of persistent connections
327 if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { 352 if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) {
328 ++$KA_COUNT{$_[1]}; 353 ++$KA_COUNT{$_[1]};
329 $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; 354 $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} };
… …
343 $state{handle}->on_eof (sub { 368 $state{handle}->on_eof (sub {
344 %state = (); 369 %state = ();
345 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); 370 $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url });
346 }); 371 });
347 372
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
348 # send request 379 # send request
349 $state{handle}->push_write ( 380 $state{handle}->push_write (
350 "$method $rpath HTTP/1.0\015\012" 381 "$method $rpath HTTP/1.0\015\012"
351 . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) 382 . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr)
352 . "\015\012" 383 . "\015\012"
353 . (delete $arg{body}) 384 . (delete $arg{body})
354 );
355
356 %hdr = (); # reduce memory usage, save a kitten
357
358 # status line
359 $state{handle}->push_read (line => qr/\015?\012/, sub {
360 $_[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 }));
362
363 my %hdr = ( # response headers
364 HTTPVersion => "\x00$1",
365 Status => "\x00$2",
366 Reason => "\x00$3",
367 URL => "\x00$url"
368 ); 385 );
369 386
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
370 # headers, could be optimized a bit 401 # headers, could be optimized a bit
371 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { 402 $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub {
372 for ("$_[1]\012") { 403 for ("$_[1]\012") {
404 y/\015//d; # weed out any \015, as they show up in the weirdest of places.
405
373 # we support spaces in field names, as lotus domino 406 # we support spaces in field names, as lotus domino
374 # creates them. 407 # creates them (actually spaces around seperators
408 # are strictly allowed in http, they are a security issue).
375 $hdr{lc $1} .= "\x00$2" 409 $hdr{lc $1} .= ",$2"
376 while /\G 410 while /\G
377 ([^:\000-\037]+): 411 ([^:\000-\037]+):
378 [\011\040]* 412 [\011\040]*
379 ((?: [^\015\012]+ | \015?\012[\011\040] )*) 413 ((?: [^\012]+ | \012[\011\040] )*)
380 \015?\012 414 \012
381 /gxc; 415 /gxc;
382 416
383 /\G$/ 417 /\G$/
384 or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); 418 or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url }));
385 } 419 }
386 420
387 substr $_, 0, 1, "" 421 substr $_, 0, 1, ""
388 for values %hdr; 422 for values %hdr;
389 423
390 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 $state{handle}->on_error (undef);
391 %state = (); 429 %state = ();
392 430
393 # set-cookie processing 431 # set-cookie processing
394 if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { 432 if ($arg{cookie_jar}) {
395 for (split /\x00/, $hdr{"set-cookie"}) { 433 for ($hdr{"set-cookie"}) {
396 my ($cookie, @arg) = split /;\s*/; 434 # parse NAME=VALUE
397 my ($name, $value) = split /=/, $cookie, 2; 435 my @kv;
398 my %kv = (value => $value, map { split /=/, $_, 2 } @arg); 436
399 437 while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) {
400 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;
401 my $cpath = (delete $kv{path}) || "/"; 457 my $cpath = (delete $kv{path}) || "/";
402 458
459 if (exists $kv{domain}) {
460 $cdom = delete $kv{domain};
461
403 $cdom =~ s/^.?/./; # make sure it starts with a "." 462 $cdom =~ s/^\.?/./; # make sure it starts with a "."
404 463
405 next if $cdom =~ /\.$/; 464 next if $cdom =~ /\.$/;
406 465
407 # this is not rfc-like and not netscape-like. go figure. 466 # this is not rfc-like and not netscape-like. go figure.
408 my $ndots = $cdom =~ y/.//; 467 my $ndots = $cdom =~ y/.//;
409 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); 468 next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2);
410 469 } else {
470 $cdom = $uhost;
471 }
472
411 # store it 473 # store it
412 $arg{cookie_jar}{version} = 1; 474 $arg{cookie_jar}{version} = 1;
413 $arg{cookie_jar}{$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 $_[0]->on_read (sub { });
414 } 531 }
415 } 532 }
416
417 if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") {
418 # microsoft and other assholes don't give a shit for following standards,
419 # try to support a common form of broken Location header.
420 $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
421
422 # apparently, mozilla et al. just change POST to GET here
423 # more research is needed before we do the same
424
425 http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
426 } elsif ($_[1]{Status} == 303 && $recurse) {
427 $_[1]{location} =~ s%^/%$scheme://$uhost:$uport/%;
428
429 http_request (GET => $_[1]{location}, %arg, recurse => $recurse - 1, $cb);
430 } else {
431 $cb->($_[0], $_[1]);
432 }
433 }; 533 });
534 });
535 };
434 536
435 if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { 537 # now handle proxy-CONNECT method
436 $finish->(undef, \%hdr); 538 if ($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;
437 } else { 550 } else {
438 if (exists $hdr{"content-length"}) { 551 %state = ();
439 $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { 552 $cb->(undef, { Status => $2, Reason => $3, URL => $url });
440 # could cache persistent connection now
441 if ($hdr{connection} =~ /\bkeep-alive\b/i) {
442 # but we don't, due to misdesigns, this is annoyingly complex
443 };
444
445 $finish->($_[1], \%hdr);
446 });
447 } else {
448 # too bad, need to read until we get an error or EOF,
449 # no way to detect winged data.
450 $_[0]->on_error (sub {
451 $finish->($_[0]{rbuf}, \%hdr);
452 });
453 $_[0]->on_eof (undef);
454 $_[0]->on_read (sub { });
455 }
456 } 553 }
457 }); 554 });
555 } else {
556 &$handle_actual_request;
458 }); 557 }
558
459 }, sub { 559 }, sub {
460 $timeout 560 $timeout
461 }; 561 };
462 }; 562 };
463 563

Diff Legend

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