package Catalyst::Engine::CGI;
-use strict;
-use base 'Catalyst::Engine';
-use URI;
+use Moose;
+extends 'Catalyst::Engine';
-require CGI::Simple;
-require CGI::Cookie;
-
-$CGI::Simple::POST_MAX = 1048576;
-$CGI::Simple::DISABLE_UPLOADS = 0;
-
-__PACKAGE__->mk_accessors('cgi');
+has _header_buf => (is => 'rw', clearer => '_clear_header_buf', predicate => '_has_header_buf');
=head1 NAME
=head1 DESCRIPTION
-This is the Catalyst engine specialized for the CGI environment (using the
-C<CGI::Simple> and C<CGI::Cookie> modules). Normally Catalyst will select the
-appropriate engine according to the environment that it detects, however you
-can force Catalyst to use the CGI engine by specifying the following in your
-application module:
+This is the Catalyst engine specialized for the CGI environment.
- use Catalyst qw(-Engine=CGI);
+=head1 PATH DECODING
-Catalyst::Engine::CGI generates a full set of HTTP headers, which means that
-applications using the engine must be be configured as "Non-parsed Headers"
-scripts (at least when running under Apache). To configure this under Apache
-name the starting with C<nph->.
+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.
-The performance of this way of using Catalyst is not expected to be
-useful in production applications, but it may be helpful for development.
+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).
-=head1 METHODS
+=head2 use_request_uri_for_path => 0
-=over 4
+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<PATH_INFO> and C<SCRIPT_NAME> environment variables.
+The allows the application to behave correctly when C<mod_rewrite> is being used to redirect requests
+into the application, as these variables are adjusted by mod_rewrite to take account for the redirect.
-=item $c->run
+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<always> decoded, and therefore Catalyst
+can't distinguish / vs %2F in paths (in addition to other encoded values).
-To be called from a CGI script to start the Catalyst application.
+=head2 use_request_uri_for_path => 1
-=item $c->cgi
+This method uses the C<REQUEST_URI> and C<SCRIPT_NAME> environment variables. As C<REQUEST_URI> is never
+decoded, this means that applications using this mode can correctly handle URIs including the %2F character
+(i.e. with C<AllowEncodedSlashes> set to C<On> in Apache).
-This config parameter contains the C<CGI::Simple> object.
+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.
-=back
+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<mod_rewrite>), the resolution of
+C<< $c->request->base >> will be incorrect.
=head1 OVERLOADED METHODS
-This class overloads some methods from C<Catalyst>.
+This class overloads some methods from C<Catalyst::Engine>.
-=over 4
-
-=item $c->finalize_headers
+=head2 $self->finalize_headers($c)
=cut
sub finalize_headers {
- my $c = shift;
- my %headers = ( -nph => 1 );
- $headers{-status} = $c->response->status if $c->response->status;
- for my $name ( $c->response->headers->header_field_names ) {
- $headers{"-$name"} = $c->response->headers->header($name);
+ my ( $self, $c ) = @_;
+
+ $c->response->header( Status => $c->response->status );
+
+ $self->_header_buf($c->response->headers->as_string("\015\012") . "\015\012");
+}
+
+=head2 $self->prepare_connection($c)
+
+=cut
+
+sub prepare_connection {
+ my ( $self, $c ) = @_;
+ local (*ENV) = $self->env || \%ENV;
+
+ my $request = $c->request;
+ $request->address( $ENV{REMOTE_ADDR} );
+
+ PROXY_CHECK:
+ {
+ unless ( ref($c)->config->{using_frontend_proxy} ) {
+ last PROXY_CHECK if $ENV{REMOTE_ADDR} ne '127.0.0.1';
+ last PROXY_CHECK if ref($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) = $ENV{HTTP_X_FORWARDED_FOR} =~ /([^,\s]+)$/;
+ $request->address($ip);
+ if ( defined $ENV{HTTP_X_FORWARDED_PORT} ) {
+ $ENV{SERVER_PORT} = $ENV{HTTP_X_FORWARDED_PORT};
+ }
}
- my @cookies;
- while ( my ( $name, $cookie ) = each %{ $c->response->cookies } ) {
- push @cookies, $c->cgi->cookie(
- -name => $name,
- -value => $cookie->{value},
- -expires => $cookie->{expires},
- -domain => $cookie->{domain},
- -path => $cookie->{path},
- -secure => $cookie->{secure} || 0
- );
+
+ $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' ) {
+ $request->secure(1);
}
- $headers{-cookie} = \@cookies if @cookies;
- print $c->cgi->header(%headers);
-}
-=item $c->finalize_output
+ if ( $ENV{SERVER_PORT} == 443 ) {
+ $request->secure(1);
+ }
+ binmode(STDOUT); # Ensure we are sending bytes.
+}
-Prints the response output to STDOUT.
+=head2 $self->prepare_headers($c)
=cut
-sub finalize_output {
- my $c = shift;
- print $c->response->output;
+sub prepare_headers {
+ my ( $self, $c ) = @_;
+ local (*ENV) = $self->env || \%ENV;
+ my $headers = $c->request->headers;
+ # Read headers from %ENV
+ foreach my $header ( keys %ENV ) {
+ next unless $header =~ /^(?:HTTP|CONTENT|COOKIE)/i;
+ ( my $field = $header ) =~ s/^HTTPS?_//;
+ $headers->header( $field => $ENV{$header} );
+ }
}
-=item $c->prepare_connection
+=head2 $self->prepare_path($c)
=cut
-sub prepare_connection {
- my $c = shift;
- $c->req->hostname( $c->cgi->remote_host );
- $c->req->address( $c->cgi->remote_addr );
-}
+# 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;
-=item $c->prepare_cookies
+ my $scheme = $c->request->secure ? 'https' : 'http';
+ my $host = $ENV{HTTP_HOST} || $ENV{SERVER_NAME};
+ my $port = $ENV{SERVER_PORT} || 80;
-Sets up cookies.
+ # fix up for IIS
+ if ($ENV{SERVER_SOFTWARE} && $ENV{SERVER_SOFTWARE} =~ m{IIS/[6-9]\.\d}) {
+ $ENV{PATH_INFO} =~ s/^\Q$ENV{SCRIPT_NAME}\E//;
+ }
-=cut
+ my $script_name = $ENV{SCRIPT_NAME};
+ $script_name =~ s/([^$URI::uric])/$URI::Escape::escapes{$1}/go if $script_name;
-sub prepare_cookies { shift->req->cookies( { CGI::Cookie->fetch } ) }
+ my $base_path;
+ if ( exists $ENV{REDIRECT_URL} ) {
+ $base_path = $ENV{REDIRECT_URL};
+ $base_path =~ s/\Q$ENV{PATH_INFO}\E$//;
+ }
+ else {
+ $base_path = $script_name || '/';
+ }
-=item $c->prepare_headers
+ # If we are running as a backend proxy, get the true hostname
+ PROXY_CHECK:
+ {
+ unless ( ref($c)->config->{using_frontend_proxy} ) {
+ last PROXY_CHECK if $host !~ /localhost|127.0.0.1/;
+ last PROXY_CHECK if ref($c)->config->{ignore_frontend_proxy};
+ }
+ last PROXY_CHECK unless $ENV{HTTP_X_FORWARDED_HOST};
+
+ $host = $ENV{HTTP_X_FORWARDED_HOST};
+
+ # 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};
+ }
+ }
-=cut
+ 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;
+ }
+ }
-sub prepare_headers {
- my $c = shift;
- $c->req->method( $c->cgi->request_method );
- for my $header ( $c->cgi->http ) {
- ( my $field = $header ) =~ s/^HTTPS?_//;
- $c->req->headers->header( $field => $c->cgi->http($header) );
+ # set the request URI
+ my $path = $base_path . ( $path_info || '' );
+ $path =~ s{^/+}{};
+
+ # Using URI directly is way too slow, so we construct the URLs manually
+ my $uri_class = "URI::$scheme";
+
+ # 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 $base_path =~ m{/$};
+
+ my $base_uri = $scheme . '://' . $host . $base_path;
+
+ $c->request->base( bless \$base_uri, $uri_class );
}
-=item $c->prepare_parameters
+=head2 $self->prepare_query_parameters($c)
=cut
-sub prepare_parameters {
- my $c = shift;
- my %vars = $c->cgi->Vars;
- while ( my ( $key, $value ) = each %vars ) {
- my @values = split "\0", $value;
- $vars{$key} = @values <= 1 ? $values[0] : \@values;
+around prepare_query_parameters => sub {
+ my $orig = shift;
+ my ( $self, $c ) = @_;
+ local (*ENV) = $self->env || \%ENV;
+
+ if ( $ENV{QUERY_STRING} ) {
+ $self->$orig( $c, $ENV{QUERY_STRING} );
}
- $c->req->parameters( {%vars} );
-}
+};
-=item $c->prepare_path
+=head2 $self->prepare_request($c, (env => \%env))
=cut
-sub prepare_path {
- my $c = shift;
- $c->req->path( $c->cgi->url( -absolute => 1, -path_info => 1 ) );
- my $loc = $c->cgi->url( -absolute => 1 );
- no warnings 'uninitialized';
- $c->req->{path} =~ s/^($loc)?\///;
- $c->req->{path} .= '/' if $c->req->path eq $loc;
- my $base = $c->cgi->url;
- if ( $ENV{CATALYST_TEST} ) {
- my $script = $c->cgi->script_name;
- $base =~ s/$script$//i;
+sub prepare_request {
+ my ( $self, $c, %args ) = @_;
+
+ if ( $args{env} ) {
+ $self->env( $args{env} );
}
- $base = URI->new($base);
- $base->path('/') if ( $ENV{CATALYST_TEST} || !$base->path );
- $c->req->base( $base->as_string );
}
-=item $c->prepare_request
+=head2 $self->prepare_write($c)
+
+Enable autoflush on the output handle for CGI-based engines.
=cut
-sub prepare_request { shift->cgi( CGI::Simple->new ) }
+around prepare_write => sub {
+ *STDOUT->autoflush(1);
+ return shift->(@_);
+};
+
+=head2 $self->write($c, $buffer)
-=item $c->prepare_uploads
+Writes the buffer to the client.
=cut
-sub prepare_uploads {
- my $c = shift;
- for my $name ( $c->cgi->upload ) {
- $c->req->uploads->{$name} = {
- fh => $c->cgi->upload($name),
- size => $c->cgi->upload_info( $name, 'size' ),
- type => $c->cgi->upload_info( $name, 'mime' )
- };
+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 ) {
+ my $headers = $self->_clear_header_buf;
+
+ $buffer = defined $buffer
+ ? $headers . $buffer : $headers;
}
-}
-sub run { shift->handler }
+ return $self->$orig( $c, $buffer );
+};
+
+=head2 $self->read_chunk($c, $buffer, $length)
+
+=cut
+
+sub read_chunk { shift; shift; *STDIN->sysread(@_); }
+
+=head2 $self->run
+
+=cut
-=back
+sub run { shift; shift->handle_request( env => \%ENV ) }
=head1 SEE ALSO
-L<Catalyst>.
+L<Catalyst>, L<Catalyst::Engine>
-=head1 AUTHOR
+=head1 AUTHORS
-Sebastian Riedel, C<sri@cpan.org>
+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;