X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2FCatalyst%2FEngine%2FCGI.pm;h=076f5b072bf8d07bb7dffc52289976eef26832cc;hb=fef8c827fc1a87b1c32c487e330b5e967874f581;hp=fae6a9aa000d778519d9f0a2885ab645f1ceebba;hpb=e701c5c61735b6aae5332b16522bbc800a626896;p=catagits%2FCatalyst-Runtime.git diff --git a/lib/Catalyst/Engine/CGI.pm b/lib/Catalyst/Engine/CGI.pm index fae6a9a..076f5b0 100644 --- a/lib/Catalyst/Engine/CGI.pm +++ b/lib/Catalyst/Engine/CGI.pm @@ -1,11 +1,9 @@ package Catalyst::Engine::CGI; -use strict; -use base 'Catalyst::Engine'; -use NEXT; -use URI; +use Moose; +extends 'Catalyst::Engine'; -__PACKAGE__->mk_accessors('env'); +has _header_buf => (is => 'rw', clearer => '_clear_header_buf', predicate => '_has_header_buf'); =head1 NAME @@ -30,6 +28,43 @@ appropriate engine module. This is the Catalyst engine specialized for the CGI environment. +=head1 PATH DECODING + +Most web server environments pass the requested path to the application using environment variables, +from which Catalyst has to reconstruct the request base (i.e. the top level path to / in the application, +exposed as C<< $c->request->base >>) and the request path below that base. + +There are two methods of doing this, both of which have advantages and disadvantages. Which method is used +is determined by the C<< $c->config(use_request_uri_for_path) >> setting (which can either be true or false). + +=head2 use_request_uri_for_path => 0 + +This is the default (and the) traditional method that Catalyst has used for determining the path information. +The path is synthesised from a combination of the C and C environment variables. +The allows the application to behave correctly when C is being used to redirect requests +into the application, as these variables are adjusted by mod_rewrite to take account for the redirect. + +However this method has the major disadvantage that it is impossible to correctly decode some elements +of the path, as RFC 3875 says: "C<< Unlike a URI path, the PATH_INFO is not URL-encoded, and cannot +contain path-segment parameters. >>" This means PATH_INFO is B decoded, and therefore Catalyst +can't distinguish / vs %2F in paths (in addition to other encoded values). + +=head2 use_request_uri_for_path => 1 + +This method uses the C and C environment variables. As C is never +decoded, this means that applications using this mode can correctly handle URIs including the %2F character +(i.e. with C set to C in Apache). + +Given that this method of path resolution is provably more correct, it is recommended that you use +this unless you have a specific need to deploy your application in a non-standard environment, and you are +aware of the implications of not being able to handle encoded URI paths correctly. + +However it also means that in a number of cases when the app isn't installed directly at a path, but instead +is having paths rewritten into it (e.g. as a .cgi/fcgi in a public_html directory, with mod_rewrite in a +.htaccess file, or when SSI is used to rewrite pages into the app, or when sub-paths of the app are exposed +at other URIs than that which the app is 'normally' based at with C), the resolution of +C<< $c->request->base >> will be incorrect. + =head1 OVERLOADED METHODS This class overloads some methods from C. @@ -43,8 +78,7 @@ sub finalize_headers { $c->response->header( Status => $c->response->status ); - print $c->response->headers->as_string("\015\012"); - print "\015\012"; + $self->_header_buf($c->response->headers->as_string("\015\012") . "\015\012"); } =head2 $self->prepare_connection($c) @@ -55,34 +89,40 @@ sub prepare_connection { my ( $self, $c ) = @_; local (*ENV) = $self->env || \%ENV; - $c->request->address( $ENV{REMOTE_ADDR} ); + my $request = $c->request; + $request->address( $ENV{REMOTE_ADDR} ); PROXY_CHECK: { - unless ( $c->config->{using_frontend_proxy} ) { + unless ( ref($c)->config->{using_frontend_proxy} ) { last PROXY_CHECK if $ENV{REMOTE_ADDR} ne '127.0.0.1'; - last PROXY_CHECK if $c->config->{ignore_frontend_proxy}; + last PROXY_CHECK if ref($c)->config->{ignore_frontend_proxy}; } last PROXY_CHECK unless $ENV{HTTP_X_FORWARDED_FOR}; # If we are running as a backend server, the user will always appear # as 127.0.0.1. Select the most recent upstream IP (last in the list) my ($ip) = $ENV{HTTP_X_FORWARDED_FOR} =~ /([^,\s]+)$/; - $c->request->address($ip); + $request->address($ip); + if ( defined $ENV{HTTP_X_FORWARDED_PORT} ) { + $ENV{SERVER_PORT} = $ENV{HTTP_X_FORWARDED_PORT}; + } } - $c->request->hostname( $ENV{REMOTE_HOST} ); - $c->request->protocol( $ENV{SERVER_PROTOCOL} ); - $c->request->user( $ENV{REMOTE_USER} ); - $c->request->method( $ENV{REQUEST_METHOD} ); + $request->hostname( $ENV{REMOTE_HOST} ) if exists $ENV{REMOTE_HOST}; + $request->protocol( $ENV{SERVER_PROTOCOL} ); + $request->user( $ENV{REMOTE_USER} ); # XXX: Deprecated. See Catalyst::Request for removal information + $request->remote_user( $ENV{REMOTE_USER} ); + $request->method( $ENV{REQUEST_METHOD} ); if ( $ENV{HTTPS} && uc( $ENV{HTTPS} ) eq 'ON' ) { - $c->request->secure(1); + $request->secure(1); } if ( $ENV{SERVER_PORT} == 443 ) { - $c->request->secure(1); + $request->secure(1); } + binmode(STDOUT); # Ensure we are sending bytes. } =head2 $self->prepare_headers($c) @@ -92,12 +132,12 @@ sub prepare_connection { sub prepare_headers { my ( $self, $c ) = @_; local (*ENV) = $self->env || \%ENV; - + my $headers = $c->request->headers; # Read headers from %ENV - while ( my ( $header, $value ) = each %ENV ) { + foreach my $header ( keys %ENV ) { next unless $header =~ /^(?:HTTP|CONTENT|COOKIE)/i; ( my $field = $header ) =~ s/^HTTPS?_//; - $c->req->headers->header( $field => $value ); + $headers->header( $field => $ENV{$header} ); } } @@ -105,6 +145,8 @@ sub prepare_headers { =cut +# Please don't touch this method without adding tests in +# t/aggregate/unit_core_engine_cgi-prepare_path.t sub prepare_path { my ( $self, $c ) = @_; local (*ENV) = $self->env || \%ENV; @@ -112,21 +154,30 @@ sub prepare_path { my $scheme = $c->request->secure ? 'https' : 'http'; my $host = $ENV{HTTP_HOST} || $ENV{SERVER_NAME}; my $port = $ENV{SERVER_PORT} || 80; + + # fix up for IIS + if ($ENV{SERVER_SOFTWARE} && $ENV{SERVER_SOFTWARE} =~ m{IIS/[6-9]\.\d}) { + $ENV{PATH_INFO} =~ s/^\Q$ENV{SCRIPT_NAME}\E//; + } + + my $script_name = $ENV{SCRIPT_NAME}; + $script_name =~ s/([^$URI::uric])/$URI::Escape::escapes{$1}/go if $script_name; + my $base_path; if ( exists $ENV{REDIRECT_URL} ) { $base_path = $ENV{REDIRECT_URL}; - $base_path =~ s/$ENV{PATH_INFO}$//; + $base_path =~ s/\Q$ENV{PATH_INFO}\E$//; } else { - $base_path = $ENV{SCRIPT_NAME} || '/'; + $base_path = $script_name || '/'; } # If we are running as a backend proxy, get the true hostname PROXY_CHECK: { - unless ( $c->config->{using_frontend_proxy} ) { + unless ( ref($c)->config->{using_frontend_proxy} ) { last PROXY_CHECK if $host !~ /localhost|127.0.0.1/; - last PROXY_CHECK if $c->config->{ignore_frontend_proxy}; + last PROXY_CHECK if ref($c)->config->{ignore_frontend_proxy}; } last PROXY_CHECK unless $ENV{HTTP_X_FORWARDED_HOST}; @@ -135,42 +186,72 @@ sub prepare_path { # backend could be on any port, so # assume frontend is on the default port $port = $c->request->secure ? 443 : 80; + if ( $ENV{HTTP_X_FORWARDED_PORT} ) { + $port = $ENV{HTTP_X_FORWARDED_PORT}; + } + } + + my $path_info = $ENV{PATH_INFO}; + if ($c->config->{use_request_uri_for_path}) { + # RFC 3875: "Unlike a URI path, the PATH_INFO is not URL-encoded, + # and cannot contain path-segment parameters." This means PATH_INFO + # is always decoded, and the script can't distinguish / vs %2F. + # See https://issues.apache.org/bugzilla/show_bug.cgi?id=35256 + # Here we try to resurrect the original encoded URI from REQUEST_URI. + if (my $req_uri = $ENV{REQUEST_URI}) { + if (defined $script_name) { + $req_uri =~ s/^\Q$script_name\E//; + } + $req_uri =~ s/\?.*$//; + $path_info = $req_uri if $req_uri; + } } - my $path = $base_path . ( $ENV{PATH_INFO} || '' ); + # set the request URI + my $path = $base_path . ( $path_info || '' ); $path =~ s{^/+}{}; - my $uri = URI->new; - $uri->scheme($scheme); - $uri->host($host); - $uri->port($port); - $uri->path($path); - $uri->query( $ENV{QUERY_STRING} ) if $ENV{QUERY_STRING}; + # Using URI directly is way too slow, so we construct the URLs manually + my $uri_class = "URI::$scheme"; - # sanitize the URI - $uri = $uri->canonical; - $c->request->uri($uri); + # HTTP_HOST will include the port even if it's 80/443 + $host =~ s/:(?:80|443)$//; + + if ( $port !~ /^(?:80|443)$/ && $host !~ /:/ ) { + $host .= ":$port"; + } + + # Escape the path + $path =~ s/([^$URI::uric])/$URI::Escape::escapes{$1}/go; + $path =~ s/\?/%3F/g; # STUPID STUPID SPECIAL CASE + + my $query = $ENV{QUERY_STRING} ? '?' . $ENV{QUERY_STRING} : ''; + my $uri = $scheme . '://' . $host . '/' . $path . $query; + + $c->request->uri( bless(\$uri, $uri_class)->canonical ); # set the base URI # base must end in a slash - $base_path .= '/' unless ( $base_path =~ /\/$/ ); - my $base = $uri->clone; - $base->path_query($base_path); - $c->request->base($base); + $base_path .= '/' unless $base_path =~ m{/$}; + + my $base_uri = $scheme . '://' . $host . $base_path; + + $c->request->base( bless \$base_uri, $uri_class ); } =head2 $self->prepare_query_parameters($c) =cut -sub prepare_query_parameters { +around prepare_query_parameters => sub { + my $orig = shift; my ( $self, $c ) = @_; local (*ENV) = $self->env || \%ENV; if ( $ENV{QUERY_STRING} ) { - $self->SUPER::prepare_query_parameters( $c, $ENV{QUERY_STRING} ); + $self->$orig( $c, $ENV{QUERY_STRING} ); } -} +}; =head2 $self->prepare_request($c, (env => \%env)) @@ -190,14 +271,28 @@ Enable autoflush on the output handle for CGI-based engines. =cut -sub prepare_write { - my ( $self, $c ) = @_; - - # Set the output handle to autoflush +around prepare_write => sub { *STDOUT->autoflush(1); + return shift->(@_); +}; - $self->NEXT::prepare_write($c); -} +=head2 $self->write($c, $buffer) + +Writes the buffer to the client. + +=cut + +around write => sub { + my $orig = shift; + my ( $self, $c, $buffer ) = @_; + + # Prepend the headers if they have not yet been sent + if ( $self->_has_header_buf ) { + $buffer = $self->_clear_header_buf . $buffer; + } + + return $self->$orig( $c, $buffer ); +}; =head2 $self->read_chunk($c, $buffer, $length) @@ -209,25 +304,22 @@ sub read_chunk { shift; shift; *STDIN->sysread(@_); } =cut -sub run { shift; shift->handle_request(@_) } +sub run { shift; shift->handle_request( env => \%ENV ) } =head1 SEE ALSO -L L. +L, L =head1 AUTHORS -Sebastian Riedel, - -Christian Hansen, - -Andy Grundman, +Catalyst Contributors, see Catalyst.pm =head1 COPYRIGHT -This program is free software, you can redistribute it and/or modify it under +This library is free software. You can redistribute it and/or modify it under the same terms as Perl itself. =cut +no Moose; 1;