… | |
… | |
48 | use AnyEvent::Socket (); |
48 | use AnyEvent::Socket (); |
49 | use AnyEvent::Handle (); |
49 | use AnyEvent::Handle (); |
50 | |
50 | |
51 | use base Exporter::; |
51 | use base Exporter::; |
52 | |
52 | |
53 | our $VERSION = '1.03'; |
53 | our $VERSION = '1.05'; |
54 | |
54 | |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
55 | our @EXPORT = qw(http_get http_post http_head http_request); |
56 | |
56 | |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
57 | our $USERAGENT = "Mozilla/5.0 (compatible; AnyEvent::HTTP/$VERSION; +http://software.schmorp.de/pkg/AnyEvent)"; |
58 | our $MAX_RECURSE = 10; |
58 | our $MAX_RECURSE = 10; |
… | |
… | |
71 | my %CO_SLOT; # number of open connections, and wait queue, per host |
71 | my %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 | |
75 | Executes an HTTP-GET request. See the http_request function for details on |
75 | Executes an HTTP-GET request. See the http_request function for details on |
76 | additional parameters. |
76 | additional 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 | |
80 | Executes an HTTP-HEAD request. See the http_request function for details on |
80 | Executes an HTTP-HEAD request. See the http_request function for details |
81 | additional parameters. |
81 | on 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, $headers) |
84 | |
84 | |
85 | Executes an HTTP-POST request with a request body of C<$bod>. See the |
85 | Executes an HTTP-POST request with a request body of C<$body>. See the |
86 | http_request function for details on additional parameters. |
86 | http_request function for details on additional parameters and the return |
|
|
87 | value. |
87 | |
88 | |
88 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
89 | =item http_request $method => $url, key => value..., $cb->($data, $headers) |
89 | |
90 | |
90 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
91 | Executes a HTTP request of type C<$method> (e.g. C<GET>, C<POST>). The URL |
91 | must be an absolute http or https URL. |
92 | must be an absolute http or https URL. |
|
|
93 | |
|
|
94 | When called in void context, nothing is returned. In other contexts, |
|
|
95 | C<http_request> returns a "cancellation guard" - you have to keep the |
|
|
96 | object at least alive until the callback get called. If the object gets |
|
|
97 | destroyed before the callbakc is called, the request will be cancelled. |
92 | |
98 | |
93 | The callback will be called with the response data as first argument |
99 | The callback will be called with the response data as first argument |
94 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
100 | (or C<undef> if it wasn't available due to errors), and a hash-ref with |
95 | response headers as second argument. |
101 | response headers as second argument. |
96 | |
102 | |
… | |
… | |
98 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
104 | headers, the "pseudo-headers" C<HTTPVersion>, C<Status> and C<Reason> |
99 | contain the three parts of the HTTP Status-Line of the same name. The |
105 | contain the three parts of the HTTP Status-Line of the same name. The |
100 | pseudo-header C<URL> contains the original URL (which can differ from the |
106 | pseudo-header C<URL> contains the original URL (which can differ from the |
101 | requested URL when following redirects). |
107 | requested URL when following redirects). |
102 | |
108 | |
103 | If the server sends a header multiple lines, then their contents will be |
109 | If the server sends a header multiple times, then their contents will be |
104 | joined together with C<\x00>. |
110 | joined together with a comma (C<,>), as per the HTTP spec. |
105 | |
111 | |
106 | If an internal error occurs, such as not being able to resolve a hostname, |
112 | If an internal error occurs, such as not being able to resolve a hostname, |
107 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
113 | then C<$data> will be C<undef>, C<< $headers->{Status} >> will be C<599> |
108 | and the C<Reason> pseudo-header will contain an error message. |
114 | and the C<Reason> pseudo-header will contain an error message. |
109 | |
115 | |
… | |
… | |
188 | my ($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 | |
|
|
200 | Example: make another simple HTTP GET request, but immediately try to |
|
|
201 | cancel 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 $request; |
193 | |
209 | |
194 | =cut |
210 | =cut |
195 | |
211 | |
196 | sub _slot_schedule; |
212 | sub _slot_schedule; |
197 | sub _slot_schedule($) { |
213 | sub _slot_schedule($) { |
… | |
… | |
221 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
237 | push @{ $CO_SLOT{$_[0]}[1] }, $_[1]; |
222 | |
238 | |
223 | _slot_schedule $_[0]; |
239 | _slot_schedule $_[0]; |
224 | } |
240 | } |
225 | |
241 | |
|
|
242 | our $qr_nl = qr<\015?\012>; |
|
|
243 | our $qr_nlnl = qr<\015?\012\015?\012>; |
|
|
244 | |
226 | sub http_request($$@) { |
245 | sub http_request($$@) { |
227 | my $cb = pop; |
246 | my $cb = pop; |
228 | my ($method, $url, %arg) = @_; |
247 | my ($method, $url, %arg) = @_; |
229 | |
248 | |
230 | my %hdr; |
249 | my %hdr; |
… | |
… | |
235 | while (my ($k, $v) = each %$hdr) { |
254 | while (my ($k, $v) = each %$hdr) { |
236 | $hdr{lc $k} = $v; |
255 | $hdr{lc $k} = $v; |
237 | } |
256 | } |
238 | } |
257 | } |
239 | |
258 | |
240 | my $recurse = exists $arg{recurse} ? $arg{recurse} : $MAX_RECURSE; |
259 | my $recurse = exists $arg{recurse} ? delete $arg{recurse} : $MAX_RECURSE; |
241 | |
260 | |
242 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) |
261 | return $cb->(undef, { Status => 599, Reason => "recursion limit reached", URL => $url }) |
243 | if $recurse < 0; |
262 | if $recurse < 0; |
244 | |
263 | |
245 | my $proxy = $arg{proxy} || $PROXY; |
264 | my $proxy = $arg{proxy} || $PROXY; |
246 | my $timeout = $arg{timeout} || $TIMEOUT; |
265 | my $timeout = $arg{timeout} || $TIMEOUT; |
247 | |
266 | |
248 | $hdr{"user-agent"} ||= $USERAGENT; |
267 | $hdr{"user-agent"} ||= $USERAGENT; |
249 | |
268 | |
250 | my ($scheme, $authority, $upath, $query, $fragment) = |
269 | my ($uscheme, $uauthority, $upath, $query, $fragment) = |
251 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
270 | $url =~ m|(?:([^:/?#]+):)?(?://([^/?#]*))?([^?#]*)(?:\?([^#]*))?(?:#(.*))?|; |
252 | |
271 | |
253 | $scheme = lc $scheme; |
272 | $uscheme = lc $uscheme; |
254 | |
273 | |
255 | my $uport = $scheme eq "http" ? 80 |
274 | my $uport = $uscheme eq "http" ? 80 |
256 | : $scheme eq "https" ? 443 |
275 | : $uscheme eq "https" ? 443 |
257 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); |
276 | : return $cb->(undef, { Status => 599, Reason => "only http and https URL schemes supported", URL => $url }); |
258 | |
277 | |
259 | $hdr{referer} ||= "$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 |
260 | |
279 | |
261 | $authority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
280 | $uauthority =~ /^(?: .*\@ )? ([^\@:]+) (?: : (\d+) )?$/x |
262 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); |
281 | or return $cb->(undef, { Status => 599, Reason => "unparsable URL", URL => $url }); |
263 | |
282 | |
264 | my $uhost = $1; |
283 | my $uhost = $1; |
265 | $uport = $2 if defined $2; |
284 | $uport = $2 if defined $2; |
266 | |
285 | |
… | |
… | |
269 | |
288 | |
270 | $upath =~ s%^/?%/%; |
289 | $upath =~ s%^/?%/%; |
271 | |
290 | |
272 | # cookie processing |
291 | # cookie processing |
273 | if (my $jar = $arg{cookie_jar}) { |
292 | if (my $jar = $arg{cookie_jar}) { |
274 | %$jar = () if $jar->{version} < 1; |
293 | %$jar = () if $jar->{version} != 1; |
275 | |
294 | |
276 | my @cookie; |
295 | my @cookie; |
277 | |
296 | |
278 | while (my ($chost, $v) = each %$jar) { |
297 | while (my ($chost, $v) = each %$jar) { |
|
|
298 | if ($chost =~ /^\./) { |
279 | next unless $chost eq substr $uhost, -length $chost; |
299 | next unless $chost eq substr $uhost, -length $chost; |
280 | next unless $chost =~ /^\./; |
300 | } elsif ($chost =~ /\./) { |
|
|
301 | next unless $chost eq $uhost; |
|
|
302 | } else { |
|
|
303 | next; |
|
|
304 | } |
281 | |
305 | |
282 | while (my ($cpath, $v) = each %$v) { |
306 | while (my ($cpath, $v) = each %$v) { |
283 | next unless $cpath eq substr $upath, 0, length $cpath; |
307 | next unless $cpath eq substr $upath, 0, length $cpath; |
284 | |
308 | |
285 | while (my ($k, $v) = each %$v) { |
309 | while (my ($k, $v) = each %$v) { |
286 | 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; |
287 | push @cookie, "$k=$v->{value}"; |
313 | push @cookie, "$k=\"$value\""; |
288 | } |
314 | } |
289 | } |
315 | } |
290 | } |
316 | } |
291 | |
317 | |
292 | $hdr{cookie} = join "; ", @cookie |
318 | $hdr{cookie} = join "; ", @cookie |
293 | if @cookie; |
319 | if @cookie; |
294 | } |
320 | } |
295 | |
321 | |
296 | my ($rhost, $rport, $rpath); # request host, port, path |
322 | my ($rhost, $rport, $rscheme, $rpath); # request host, port, path |
297 | |
323 | |
298 | if ($proxy) { |
324 | if ($proxy) { |
299 | ($rhost, $rport, $scheme) = @$proxy; |
325 | ($rhost, $rport, $rscheme, $rpath) = (@$proxy, $url); |
300 | $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" && $rscheme eq "https"; |
301 | } else { |
330 | } else { |
302 | ($rhost, $rport, $rpath) = ($uhost, $uport, $upath); |
331 | ($rhost, $rport, $rscheme, $rpath) = ($uhost, $uport, $uscheme, $upath); |
303 | $hdr{host} = $uhost; |
|
|
304 | } |
332 | } |
305 | |
333 | |
|
|
334 | $hdr{host} = $uhost; |
306 | $hdr{"content-length"} = length $arg{body}; |
335 | $hdr{"content-length"} = length $arg{body}; |
307 | |
336 | |
308 | my %state = (connect_guard => 1); |
337 | my %state = (connect_guard => 1); |
309 | |
338 | |
310 | _get_slot $uhost, sub { |
339 | _get_slot $uhost, sub { |
… | |
… | |
313 | return unless $state{connect_guard}; |
342 | return unless $state{connect_guard}; |
314 | |
343 | |
315 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
344 | $state{connect_guard} = AnyEvent::Socket::tcp_connect $rhost, $rport, sub { |
316 | $state{fh} = shift |
345 | $state{fh} = shift |
317 | or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); |
346 | or return $cb->(undef, { Status => 599, Reason => "$!", URL => $url }); |
|
|
347 | pop; # free memory, save a tree |
318 | |
348 | |
319 | delete $state{connect_guard}; # reduce memory usage, save a tree |
349 | return unless delete $state{connect_guard}; |
320 | |
350 | |
321 | # get handle |
351 | # get handle |
322 | $state{handle} = new AnyEvent::Handle |
352 | $state{handle} = new AnyEvent::Handle |
323 | fh => $state{fh}, |
353 | fh => $state{fh}, |
324 | ($scheme eq "https" ? (tls => "connect") : ()); |
354 | timeout => $timeout; |
325 | |
355 | |
326 | # limit the number of persistent connections |
356 | # limit the number of persistent connections |
|
|
357 | # keepalive not yet supported |
327 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
358 | if ($KA_COUNT{$_[1]} < $MAX_PERSISTENT_PER_HOST) { |
328 | ++$KA_COUNT{$_[1]}; |
359 | ++$KA_COUNT{$_[1]}; |
329 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { --$KA_COUNT{$_[1]} }; |
360 | $state{handle}{ka_count_guard} = AnyEvent::Util::guard { |
|
|
361 | --$KA_COUNT{$_[1]} |
|
|
362 | }; |
330 | $hdr{connection} = "keep-alive"; |
363 | $hdr{connection} = "keep-alive"; |
331 | delete $hdr{connection}; # keep-alive not yet supported |
|
|
332 | } else { |
364 | } else { |
333 | delete $hdr{connection}; |
365 | delete $hdr{connection}; |
334 | } |
366 | } |
335 | |
367 | |
336 | # (re-)configure handle |
368 | # (re-)configure handle |
337 | $state{handle}->timeout ($timeout); |
|
|
338 | $state{handle}->on_error (sub { |
369 | $state{handle}->on_error (sub { |
339 | my $errno = "$!"; |
370 | my $errno = "$!"; |
340 | %state = (); |
371 | %state = (); |
341 | $cb->(undef, { Status => 599, Reason => $errno, URL => $url }); |
372 | $cb->(undef, { Status => 599, Reason => $errno, URL => $url }); |
342 | }); |
373 | }); |
343 | $state{handle}->on_eof (sub { |
374 | $state{handle}->on_eof (sub { |
344 | %state = (); |
375 | %state = (); |
345 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); |
376 | $cb->(undef, { Status => 599, Reason => "unexpected end-of-file", URL => $url }); |
346 | }); |
377 | }); |
347 | |
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 | |
348 | # send request |
385 | # send request |
349 | $state{handle}->push_write ( |
386 | $state{handle}->push_write ( |
350 | "$method $rpath HTTP/1.0\015\012" |
387 | "$method $rpath HTTP/1.0\015\012" |
351 | . (join "", map "$_: $hdr{$_}\015\012", keys %hdr) |
388 | . (join "", map "\u$_: $hdr{$_}\015\012", keys %hdr) |
352 | . "\015\012" |
389 | . "\015\012" |
353 | . (delete $arg{body}) |
390 | . (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 | ); |
391 | ); |
369 | |
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 | |
370 | # headers, could be optimized a bit |
407 | # headers, could be optimized a bit |
371 | $state{handle}->unshift_read (line => qr/\015?\012\015?\012/, sub { |
408 | $state{handle}->unshift_read (line => $qr_nlnl, sub { |
372 | for ("$_[1]\012") { |
409 | for ("$_[1]\012") { |
|
|
410 | y/\015//d; # weed out any \015, as they show up in the weirdest of places. |
|
|
411 | |
373 | # we support spaces in field names, as lotus domino |
412 | # we support spaces in field names, as lotus domino |
374 | # creates them. |
413 | # creates them (actually spaces around seperators |
|
|
414 | # are strictly allowed in http, they are a security issue). |
375 | $hdr{lc $1} .= "\x00$2" |
415 | $hdr{lc $1} .= ",$2" |
376 | while /\G |
416 | while /\G |
377 | ([^:\000-\037]+): |
417 | ([^:\000-\037]+): |
378 | [\011\040]* |
418 | [\011\040]* |
379 | ((?: [^\015\012]+ | \015?\012[\011\040] )*) |
419 | ((?: [^\012]+ | \012[\011\040] )*) |
380 | \015?\012 |
420 | \012 |
381 | /gxc; |
421 | /gxc; |
382 | |
422 | |
383 | /\G$/ |
423 | /\G$/ |
384 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); |
424 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "garbled response headers", URL => $url })); |
385 | } |
425 | } |
386 | |
426 | |
387 | substr $_, 0, 1, "" |
427 | substr $_, 0, 1, "" |
388 | for values %hdr; |
428 | for values %hdr; |
389 | |
429 | |
390 | my $finish = sub { |
430 | my $finish = sub { |
|
|
431 | # TODO: use destroy method, when/if available |
|
|
432 | #$state{handle}->destroy; |
|
|
433 | $state{handle}->on_eof (undef); |
|
|
434 | $state{handle}->on_error (undef); |
391 | %state = (); |
435 | %state = (); |
392 | |
436 | |
393 | # set-cookie processing |
437 | # set-cookie processing |
394 | if ($arg{cookie_jar} && exists $hdr{"set-cookie"}) { |
438 | if ($arg{cookie_jar}) { |
395 | for (split /\x00/, $hdr{"set-cookie"}) { |
439 | for ($hdr{"set-cookie"}) { |
396 | my ($cookie, @arg) = split /;\s*/; |
440 | # parse NAME=VALUE |
397 | my ($name, $value) = split /=/, $cookie, 2; |
441 | my @kv; |
398 | my %kv = (value => $value, map { split /=/, $_, 2 } @arg); |
442 | |
399 | |
443 | while (/\G\s* ([^=;,[:space:]]+) \s*=\s* (?: "((?:[^\\"]+|\\.)*)" | ([^=;,[:space:]]*) )/gcxs) { |
400 | my $cdom = (delete $kv{domain}) || $uhost; |
444 | my $name = $1; |
|
|
445 | my $value = $3; |
|
|
446 | |
|
|
447 | unless ($value) { |
|
|
448 | $value = $2; |
|
|
449 | $value =~ s/\\(.)/$1/gs; |
|
|
450 | } |
|
|
451 | |
|
|
452 | push @kv, $name => $value; |
|
|
453 | |
|
|
454 | last unless /\G\s*;/gc; |
|
|
455 | } |
|
|
456 | |
|
|
457 | last unless @kv; |
|
|
458 | |
|
|
459 | my $name = shift @kv; |
|
|
460 | my %kv = (value => shift @kv, @kv); |
|
|
461 | |
|
|
462 | my $cdom; |
401 | my $cpath = (delete $kv{path}) || "/"; |
463 | my $cpath = (delete $kv{path}) || "/"; |
402 | |
464 | |
|
|
465 | if (exists $kv{domain}) { |
|
|
466 | $cdom = delete $kv{domain}; |
|
|
467 | |
403 | $cdom =~ s/^.?/./; # make sure it starts with a "." |
468 | $cdom =~ s/^\.?/./; # make sure it starts with a "." |
404 | |
469 | |
405 | next if $cdom =~ /\.$/; |
470 | next if $cdom =~ /\.$/; |
406 | |
471 | |
407 | # this is not rfc-like and not netscape-like. go figure. |
472 | # this is not rfc-like and not netscape-like. go figure. |
408 | my $ndots = $cdom =~ y/.//; |
473 | my $ndots = $cdom =~ y/.//; |
409 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
474 | next if $ndots < ($cdom =~ /\.[^.][^.]\.[^.][^.]$/ ? 3 : 2); |
410 | |
475 | } else { |
|
|
476 | $cdom = $uhost; |
|
|
477 | } |
|
|
478 | |
411 | # store it |
479 | # store it |
412 | $arg{cookie_jar}{version} = 1; |
480 | $arg{cookie_jar}{version} = 1; |
413 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
481 | $arg{cookie_jar}{$cdom}{$cpath}{$name} = \%kv; |
|
|
482 | |
|
|
483 | redo if /\G\s*,/gc; |
|
|
484 | } |
|
|
485 | } |
|
|
486 | |
|
|
487 | # microsoft and other shitheads don't give a shit for following standards, |
|
|
488 | # try to support some common forms of broken Location headers. |
|
|
489 | if ($_[1]{location} !~ /^(?: $ | [^:\/?\#]+ : )/x) { |
|
|
490 | $_[1]{location} =~ s/^\.\/+//; |
|
|
491 | |
|
|
492 | my $url = "$rscheme://$uhost:$uport"; |
|
|
493 | |
|
|
494 | unless ($_[1]{location} =~ s/^\///) { |
|
|
495 | $url .= $upath; |
|
|
496 | $url =~ s/\/[^\/]*$//; |
|
|
497 | } |
|
|
498 | |
|
|
499 | $_[1]{location} = "$url/$_[1]{location}"; |
|
|
500 | } |
|
|
501 | |
|
|
502 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse && $method ne "POST") { |
|
|
503 | # apparently, mozilla et al. just change POST to GET here |
|
|
504 | # more research is needed before we do the same |
|
|
505 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
506 | } elsif ($_[1]{Status} == 303 && $recurse) { |
|
|
507 | # even http/1.1 is unclear on how to mutate the method |
|
|
508 | $method = "GET" unless $method eq "HEAD"; |
|
|
509 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
510 | } elsif ($_[1]{Status} == 307 && $recurse && $method =~ /^(?:GET|HEAD)$/) { |
|
|
511 | http_request ($method => $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
512 | } else { |
|
|
513 | $cb->($_[0], $_[1]); |
|
|
514 | } |
|
|
515 | }; |
|
|
516 | |
|
|
517 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
|
|
518 | $finish->(undef, \%hdr); |
|
|
519 | } else { |
|
|
520 | if (exists $hdr{"content-length"}) { |
|
|
521 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
|
|
522 | # could cache persistent connection now |
|
|
523 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
524 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
525 | }; |
|
|
526 | |
|
|
527 | $finish->($_[1], \%hdr); |
|
|
528 | }); |
|
|
529 | } else { |
|
|
530 | # too bad, need to read until we get an error or EOF, |
|
|
531 | # no way to detect winged data. |
|
|
532 | $_[0]->on_error (sub { |
|
|
533 | $finish->($_[0]{rbuf}, \%hdr); |
|
|
534 | }); |
|
|
535 | $_[0]->on_eof (undef); |
|
|
536 | $_[0]->on_read (sub { }); |
414 | } |
537 | } |
415 | } |
538 | } |
416 | |
|
|
417 | if ($_[1]{Status} =~ /^30[12]$/ && $recurse) { |
|
|
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 | http_request ($method, $_[1]{location}, %arg, recurse => $recurse - 1, $cb); |
|
|
423 | } else { |
|
|
424 | $cb->($_[0], $_[1]); |
|
|
425 | } |
|
|
426 | }; |
539 | }); |
|
|
540 | }); |
|
|
541 | }; |
427 | |
542 | |
428 | if ($hdr{Status} =~ /^(?:1..|204|304)$/ or $method eq "HEAD") { |
543 | # now handle proxy-CONNECT method |
429 | $finish->(undef, \%hdr); |
544 | if ($proxy && $uscheme eq "https") { |
|
|
545 | # oh dear, we have to wrap it into a connect request |
|
|
546 | |
|
|
547 | # maybe re-use $uauthority with patched port? |
|
|
548 | $state{handle}->push_write ("CONNECT $uhost:$uport HTTP/1.0\015\012Host: $uhost\015\012\015\012"); |
|
|
549 | $state{handle}->push_read (line => $qr_nlnl, sub { |
|
|
550 | $_[1] =~ /^HTTP\/([0-9\.]+) \s+ ([0-9]{3}) (?: \s+ ([^\015\012]*) )?/ix |
|
|
551 | or return (%state = (), $cb->(undef, { Status => 599, Reason => "invalid proxy connect response ($_[1])", URL => $url })); |
|
|
552 | |
|
|
553 | if ($2 == 200) { |
|
|
554 | $rpath = $upath; |
|
|
555 | &$handle_actual_request; |
430 | } else { |
556 | } else { |
431 | if (exists $hdr{"content-length"}) { |
557 | %state = (); |
432 | $_[0]->unshift_read (chunk => $hdr{"content-length"}, sub { |
558 | $cb->(undef, { Status => $2, Reason => $3, URL => $url }); |
433 | # could cache persistent connection now |
|
|
434 | if ($hdr{connection} =~ /\bkeep-alive\b/i) { |
|
|
435 | # but we don't, due to misdesigns, this is annoyingly complex |
|
|
436 | }; |
|
|
437 | |
|
|
438 | $finish->($_[1], \%hdr); |
|
|
439 | }); |
|
|
440 | } else { |
|
|
441 | # too bad, need to read until we get an error or EOF, |
|
|
442 | # no way to detect winged data. |
|
|
443 | $_[0]->on_error (sub { |
|
|
444 | $finish->($_[0]{rbuf}, \%hdr); |
|
|
445 | }); |
|
|
446 | $_[0]->on_eof (undef); |
|
|
447 | $_[0]->on_read (sub { }); |
|
|
448 | } |
|
|
449 | } |
559 | } |
450 | }); |
560 | }); |
|
|
561 | } else { |
|
|
562 | &$handle_actual_request; |
451 | }); |
563 | } |
|
|
564 | |
452 | }, sub { |
565 | }, sub { |
453 | $timeout |
566 | $timeout |
454 | }; |
567 | }; |
455 | }; |
568 | }; |
456 | |
569 | |