gitweb: Allow UTF-8 encoded CGI query parameters and path_info

[git.git] / gitweb / gitweb.perl

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index f80f2594cb2e498fa788d38f5b06c88e2fef95ca..6cfe8d932de0e62b745a3242fa0e945e26fbc76b 100755 (executable)
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -52,7 +52,7 @@ sub evaluate_uri {
        # as base URL.
        # Therefore, if we needed to strip PATH_INFO, then we know that we have
        # to build the base URL ourselves:
-       our $path_info = $ENV{"PATH_INFO"};
+       our $path_info = decode_utf8($ENV{"PATH_INFO"});
        if ($path_info) {
                if ($my_url =~ s,\Q$path_info\E$,, &&
                    $my_uri =~ s,\Q$path_info\E$,, &&
@@ -816,9 +816,9 @@ sub evaluate_query_params {
 
        while (my ($name, $symbol) = each %cgi_param_mapping) {
                if ($symbol eq 'opt') {
-                       $input_params{$name} = [ $cgi->param($symbol) ];
+                       $input_params{$name} = [ map { decode_utf8($_) } $cgi->param($symbol) ];
                } else {
-                       $input_params{$name} = $cgi->param($symbol);
+                       $input_params{$name} = decode_utf8($cgi->param($symbol));
                }
        }
 }
@@ -1443,8 +1443,8 @@ sub validate_refname {
 sub to_utf8 {
        my $str = shift;
        return undef unless defined $str;
-       if (utf8::valid($str)) {
-               utf8::decode($str);
+
+       if (utf8::is_utf8($str) || utf8::decode($str)) {
                return $str;
        } else {
                return decode($fallback_encoding, $str, Encode::FB_DEFAULT);
@@ -1696,6 +1696,7 @@ sub chop_and_escape_str {
        my ($str) = @_;
 
        my $chopped = chop_str(@_);
+       $str = to_utf8($str);
        if ($chopped eq $str) {
                return esc_html($chopped);
        } else {
@@ -2764,7 +2765,7 @@ sub git_populate_project_tagcloud {
        }
 
        my $cloud;
-       my $matched = $cgi->param('by_tag');
+       my $matched = $input_params{'ctag'};
        if (eval { require HTML::TagCloud; 1; }) {
                $cloud = HTML::TagCloud->new;
                foreach my $ctag (sort keys %ctags_lc) {
@@ -2835,8 +2836,8 @@ sub git_get_projects_list {
                my $dir = $projects_list;
                # remove the trailing "/"
                $dir =~ s!/+$!!;
-               my $pfxlen = length("$projects_list");
-               my $pfxdepth = ($projects_list =~ tr!/!!);
+               my $pfxlen = length("$dir");
+               my $pfxdepth = ($dir =~ tr!/!!);
                # when filtering, search only given subdirectory
                if ($filter) {
                        $dir .= "/$filter";
@@ -3870,7 +3871,7 @@ sub print_search_form {
                               -values => ['commit', 'grep', 'author', 'committer', 'pickaxe']) .
              $cgi->sup($cgi->a({-href => href(action=>"search_help")}, "?")) .
              " search:\n",
-             $cgi->textfield(-name => "s", -value => $searchtext) . "\n" .
+             $cgi->textfield(-name => "s", -value => $searchtext, -override => 1) . "\n" .
              "<span title=\"Extended regular expression\">" .
              $cgi->checkbox(-name => 'sr', -value => 1, -label => 're',
                             -checked => $search_use_regexp) .
@@ -5279,7 +5280,7 @@ sub git_project_list_body {
 
        my $check_forks = gitweb_check_feature('forks');
        my $show_ctags  = gitweb_check_feature('ctags');
-       my $tagfilter = $show_ctags ? $cgi->param('by_tag') : undef;
+       my $tagfilter = $show_ctags ? $input_params{'ctag'} : undef;
        $check_forks = undef
                if ($tagfilter || $searchtext);
 
@@ -5835,7 +5836,7 @@ sub git_search_files {
        my %co = @_;
 
        local $/ = "\n";
-       open my $fd, "-|", git_cmd(), 'grep', '-n',
+       open my $fd, "-|", git_cmd(), 'grep', '-n', '-z',
                $search_use_regexp ? ('-E', '-i') : '-F',
                $searchtext, $co{'tree'}
                        or die_error(500, "Open git-grep failed");
@@ -5851,13 +5852,14 @@ sub git_search_files {
        my $lastfile = '';
        while (my $line = <$fd>) {
                chomp $line;
-               my ($file, $lno, $ltext, $binary);
+               my ($file, $file_href, $lno, $ltext, $binary);
                last if ($matches++ > 1000);
                if ($line =~ /^Binary file (.+) matches$/) {
                        $file = $1;
                        $binary = 1;
                } else {
-                       (undef, $file, $lno, $ltext) = split(/:/, $line, 4);
+                       ($file, $lno, $ltext) = split(/\0/, $line, 3);
+                       $file =~ s/^$co{'tree'}://;
                }
                if ($file ne $lastfile) {
                        $lastfile and print "</td></tr>\n";
@@ -5866,10 +5868,10 @@ sub git_search_files {
                        } else {
                                print "<tr class=\"light\">\n";
                        }
+                       $file_href = href(action=>"blob", hash_base=>$co{'id'},
+                                         file_name=>$file);
                        print "<td class=\"list\">".
-                               $cgi->a({-href => href(action=>"blob", hash=>$co{'hash'},
-                                                      file_name=>"$file"),
-                                       -class => "list"}, esc_path($file));
+                               $cgi->a({-href => $file_href, -class => "list"}, esc_path($file));
                        print "</td><td>\n";
                        $lastfile = $file;
                }
@@ -5887,10 +5889,9 @@ sub git_search_files {
                                $ltext = esc_html($ltext, -nbsp=>1);
                        }
                        print "<div class=\"pre\">" .
-                               $cgi->a({-href => href(action=>"blob", hash=>$co{'hash'},
-                                                      file_name=>"$file").'#l'.$lno,
-                                       -class => "linenr"}, sprintf('%4i', $lno))
-                               . ' ' .  $ltext . "</div>\n";
+                               $cgi->a({-href => $file_href.'#l'.$lno,
+                                       -class => "linenr"}, sprintf('%4i', $lno)) .
+                               ' ' .  $ltext . "</div>\n";
                }
        }
        if ($lastfile) {
@@ -5991,7 +5992,7 @@ sub git_project_list {
        }
        print $cgi->startform(-method => "get") .
              "<p class=\"projsearch\">Search:\n" .
-             $cgi->textfield(-name => "s", -value => $searchtext) . "\n" .
+             $cgi->textfield(-name => "s", -value => $searchtext, -override => 1) . "\n" .
              "</p>" .
              $cgi->end_form() . "\n";
        git_project_list_body(\@list, $order);
@@ -6194,7 +6195,7 @@ sub git_tag {
 
 sub git_blame_common {
        my $format = shift || 'porcelain';
-       if ($format eq 'porcelain' && $cgi->param('js')) {
+       if ($format eq 'porcelain' && $input_params{'javascript'}) {
                $format = 'incremental';
                $action = 'blame_incremental'; # for page title etc
        }
@@ -6243,7 +6244,9 @@ sub git_blame_common {
                        -type=>"text/plain", -charset => "utf-8",
                        -status=> "200 OK");
                local $| = 1; # output autoflush
-               print while <$fd>;
+               while (my $line = <$fd>) {
+                       print to_utf8($line);
+               }
                close $fd
                        or print "ERROR $!\n";
 
@@ -7862,11 +7865,12 @@ sub git_opml {
                -charset => 'utf-8',
                -content_disposition => 'inline; filename="opml.xml"');
 
+       my $title = esc_html($site_name);
        print <<XML;
 <?xml version="1.0" encoding="utf-8"?>
 <opml version="1.0">
 <head>
-  <title>$site_name OPML Export</title>
+  <title>$title OPML Export</title>
 </head>
 <body>
 <outline text="git RSS feeds">