gitweb: Fix handling of whitespace in generated links

When creating path_info part of link, don't encode space as '+', because
while $cgi->param('foo') translates '+' in query param to ' ', neither
$ENV{'PATH_INFO'} nor $cgi->path_info() do.

This fixes the issue with pathnames with embedded whitespace and
$feature{'pathinfo'} / path_info links.  It is done by using newly
introduced esc_path_info() instead of esc_url() in href() subroutine.

Also while links are more clear not escaping space (' ') characters in
generated links, the trailing space must be URI-encoded, otherwise would
get discarded.

Issue noticed thanks to John 'Warthog9' Hawley.

Signed-off-by: Jakub Narebski <jnareb@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index e645d4a821f7eab28911f508923abd3e9a9dc53b..75cef245a26f24d4aefd19a7b9b6edea9676b2ba 100755 (executable)
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -1186,7 +1186,7 @@ sub href {
                $href =~ s,/$,,;
 
                # Then add the project name, if present
                $href =~ s,/$,,;
 
                # Then add the project name, if present

-               $href .= "/".esc_url($params{'project'});
+               $href .= "/".esc_path_info($params{'project'});

                delete $params{'project'};
 
                # since we destructively absorb parameters, we keep this
                delete $params{'project'};
 
                # since we destructively absorb parameters, we keep this


@@ -1196,7 +1196,8 @@ sub href {
                # Summary just uses the project path URL, any other action is
                # added to the URL
                if (defined $params{'action'}) {
                # Summary just uses the project path URL, any other action is
                # added to the URL
                if (defined $params{'action'}) {

-                       $href .= "/".esc_url($params{'action'}) unless $params{'action'} eq 'summary';
+                       $href .= "/".esc_path_info($params{'action'})
+                               unless $params{'action'} eq 'summary';

                        delete $params{'action'};
                }
 
                        delete $params{'action'};
                }
 


@@ -1206,13 +1207,13 @@ sub href {
                        || $params{'hash_parent'} || $params{'hash'});
                if (defined $params{'hash_base'}) {
                        if (defined $params{'hash_parent_base'}) {
                        || $params{'hash_parent'} || $params{'hash'});
                if (defined $params{'hash_base'}) {
                        if (defined $params{'hash_parent_base'}) {

-                               $href .= esc_url($params{'hash_parent_base'});
+                               $href .= esc_path_info($params{'hash_parent_base'});

                                # skip the file_parent if it's the same as the file_name
                                if (defined $params{'file_parent'}) {
                                        if (defined $params{'file_name'} && $params{'file_parent'} eq $params{'file_name'}) {
                                                delete $params{'file_parent'};
                                        } elsif ($params{'file_parent'} !~ /\.\./) {
                                # skip the file_parent if it's the same as the file_name
                                if (defined $params{'file_parent'}) {
                                        if (defined $params{'file_name'} && $params{'file_parent'} eq $params{'file_name'}) {
                                                delete $params{'file_parent'};
                                        } elsif ($params{'file_parent'} !~ /\.\./) {

-                                               $href .= ":/".esc_url($params{'file_parent'});
+                                               $href .= ":/".esc_path_info($params{'file_parent'});

                                                delete $params{'file_parent'};
                                        }
                                }
                                                delete $params{'file_parent'};
                                        }
                                }


@@ -1220,19 +1221,19 @@ sub href {
                                delete $params{'hash_parent'};
                                delete $params{'hash_parent_base'};
                        } elsif (defined $params{'hash_parent'}) {
                                delete $params{'hash_parent'};
                                delete $params{'hash_parent_base'};
                        } elsif (defined $params{'hash_parent'}) {

-                               $href .= esc_url($params{'hash_parent'}). "..";
+                               $href .= esc_path_info($params{'hash_parent'}). "..";

                                delete $params{'hash_parent'};
                        }
 
                                delete $params{'hash_parent'};
                        }
 

-                       $href .= esc_url($params{'hash_base'});
+                       $href .= esc_path_info($params{'hash_base'});

                        if (defined $params{'file_name'} && $params{'file_name'} !~ /\.\./) {
                        if (defined $params{'file_name'} && $params{'file_name'} !~ /\.\./) {

-                               $href .= ":/".esc_url($params{'file_name'});
+                               $href .= ":/".esc_path_info($params{'file_name'});

                                delete $params{'file_name'};
                        }
                        delete $params{'hash'};
                        delete $params{'hash_base'};
                } elsif (defined $params{'hash'}) {
                                delete $params{'file_name'};
                        }
                        delete $params{'hash'};
                        delete $params{'hash_base'};
                } elsif (defined $params{'hash'}) {

-                       $href .= esc_url($params{'hash'});
+                       $href .= esc_path_info($params{'hash'});

                        delete $params{'hash'};
                }
 
                        delete $params{'hash'};
                }
 


@@ -1265,6 +1266,9 @@ sub href {
        }
        $href .= "?" . join(';', @result) if scalar @result;
 
        }
        $href .= "?" . join(';', @result) if scalar @result;
 

+       # final transformation: trailing spaces must be escaped (URI-encoded)
+       $href =~ s/(\s+)$/CGI::escape($1)/e;
+

        return $href;
 }
 
        return $href;
 }
 


@@ -1347,6 +1351,17 @@ sub esc_param {
        return $str;
 }
 
        return $str;
 }
 

+# the quoting rules for path_info fragment are slightly different
+sub esc_path_info {
+       my $str = shift;
+       return undef unless defined $str;
+
+       # path_info doesn't treat '+' as space (specially), but '?' must be escaped
+       $str =~ s/([^A-Za-z0-9\-_.~();\/;:@&= +]+)/CGI::escape($1)/eg;
+
+       return $str;
+}
+

 # quote unsafe chars in whole URL, so some characters cannot be quoted
 sub esc_url {
        my $str = shift;
 # quote unsafe chars in whole URL, so some characters cannot be quoted
 sub esc_url {
        my $str = shift;