gitweb: Handle non UTF-8 text better

gitweb assumes that everything is in UTF-8. If a text contains invalid
UTF-8 character sequences, the text must be in a different encoding.

This commit introduces $fallback_encoding which would be used as input
encoding if gitweb encounters text with is not valid UTF-8.

Add basic test for this in t/t9500-gitweb-standalone-no-errors.sh

Signed-off-by: Martin Koegler <redacted>
Signed-off-by: Jakub Narebski <redacted>
Tested-by: Alexandre Julliard <redacted>
Tested-by: Ismail Dönmez <redacted>
Signed-off-by: Junio C Hamano <redacted>

diff --git a/gitweb.perl b/gitweb.perl
index 5c7afb7f1d998d31c62bac633f6e776eb9201150a22cf0621694f189927f98b4..47dcc9c9abbb9280bb37960b12a69795e373ac20a868e9a9042b240cdf7b2a8f 100755 (executable)
--- a/gitweb.perl
+++ b/gitweb.perl
@@ -95,6 +95,13 @@ our $default_text_plain_charset  = undef;
 # (relative to the current git repository)
 our $mimetypes_file = undef;
 
+# assume this charset if line contains non-UTF-8 characters;
+# it should be valid encoding (see Encoding::Supported(3pm) for list),
+# for which encoding all byte sequences are valid, for example
+# 'iso-8859-1' aka 'latin1' (it is decoded without checking, so it
+# could be even 'utf-8' for the old behavior)
+our $fallback_encoding = 'latin1';
+
 # You define site-wide feature defaults here; override them with
 # $GITWEB_CONFIG as necessary.
 our %feature = (
@@ -603,6 +610,20 @@ sub validate_refname {
        return $input;
 }
 
+# decode sequences of octets in utf8 into Perl's internal form,
+# which is utf-8 with utf8 flag set if needed.  gitweb writes out
+# in utf-8 thanks to "binmode STDOUT, ':utf8'" at beginning
+sub to_utf8 {
+       my $str = shift;
+       my $res;
+       eval { $res = decode_utf8($str, Encode::FB_CROAK); };
+       if (defined $res) {
+               return $res;
+       } else {
+               return decode($fallback_encoding, $str, Encode::FB_DEFAULT);
+       }
+}
+
 # quote unsafe chars, but keep the slash, even when it's not
 # correct, but quoted slashes look too horrible in bookmarks
 sub esc_param {
@@ -627,7 +648,7 @@ sub esc_html ($;%) {
        my $str = shift;
        my %opts = @_;
 
-       $str = decode_utf8($str);
+       $str = to_utf8($str);
        $str = $cgi->escapeHTML($str);
        if ($opts{'-nbsp'}) {
                $str =~ s/ / /g;
@@ -641,7 +662,7 @@ sub esc_path {
        my $str = shift;
        my %opts = @_;
 
-       $str = decode_utf8($str);
+       $str = to_utf8($str);
        $str = $cgi->escapeHTML($str);
        if ($opts{'-nbsp'}) {
                $str =~ s/ / /g;
@@ -926,7 +947,7 @@ sub format_subject_html {
 
        if (length($short) < length($long)) {
                return $cgi->a({-href => $href, -class => "list subject",
-                               -title => decode_utf8($long)},
+                               -title => to_utf8($long)},
                       esc_html($short) . $extra);
        } else {
                return $cgi->a({-href => $href, -class => "list subject"},
@@ -1240,7 +1261,7 @@ sub git_get_projects_list {
                        if (check_export_ok("$projectroot/$path")) {
                                my $pr = {
                                        path => $path,
-                                       owner => decode_utf8($owner),
+                                       owner => to_utf8($owner),
                                };
                                push @list, $pr;
                                (my $forks_path = $path) =~ s/\.git$//;
@@ -1270,7 +1291,7 @@ sub git_get_project_owner {
                        $pr = unescape($pr);
                        $ow = unescape($ow);
                        if ($pr eq $project) {
-                               $owner = decode_utf8($ow);
+                               $owner = to_utf8($ow);
                                last;
                        }
                }
@@ -1760,7 +1781,7 @@ sub get_file_owner {
        }
        my $owner = $gcos;
        $owner =~ s/[,;].*$//;
-       return decode_utf8($owner);
+       return to_utf8($owner);
 }
 
 ## ......................................................................
@@ -1843,7 +1864,7 @@ sub git_header_html {
 
        my $title = "$site_name";
        if (defined $project) {
-               $title .= " - " . decode_utf8($project);
+               $title .= " - " . to_utf8($project);
                if (defined $action) {
                        $title .= "/$action";
                        if (defined $file_name) {
@@ -2117,7 +2138,7 @@ sub git_print_page_path {
 
        print "<div class=\"page_path\">";
        print $cgi->a({-href => href(action=>"tree", hash_base=>$hb),
-                     -title => 'tree root'}, decode_utf8("[$project]"));
+                     -title => 'tree root'}, to_utf8("[$project]"));
        print " / ";
        if (defined $name) {
                my @dirname = split '/', $name;
@@ -2937,7 +2958,7 @@ sub git_project_list_body {
                ($pr->{'age'}, $pr->{'age_string'}) = @aa;
                if (!defined $pr->{'descr'}) {
                        my $descr = git_get_project_description($pr->{'path'}) || "";
-                       $pr->{'descr_long'} = decode_utf8($descr);
+                       $pr->{'descr_long'} = to_utf8($descr);
                        $pr->{'descr'} = chop_str($descr, 25, 5);
                }
                if (!defined $pr->{'owner'}) {
@@ -3982,7 +4003,7 @@ sub git_snapshot {
        my $git = git_cmd_str();
        my $name = $project;
        $name =~ s/\047/\047\\\047\047/g;
-       my $filename = decode_utf8(basename($project));
+       my $filename = to_utf8(basename($project));
        my $cmd;
        if ($suffix eq 'zip') {
                $filename .= "-$hash.$suffix";