gitweb: safely output binary files for 'blob_plain' action

gitweb tries now to output correct Content-Type header for
'blob_plain' action; for now text/plain for text files,
appropriate image MIME type for *.png, *.gif and *.jpg/*.jpeg files,
and application/octet-stream for other binary files.

Introduced new configuration variables: $default_blob_plain_mimetype
and $default_text_plain_charset (only 'utf-8' is guaranteed to work
for the latter).

binmode changed to ':raw' in git_blob_plain for output of non-text files.

Signed-off-by: Junio C Hamano <redacted>

diff --git a/gitweb.cgi b/gitweb.cgi
index 1708308913cc54f272d913209464406f23faf38586da29831c7beef370264437..77b4c23e5cdb0c9d1694ada023060d2cec3421f9f40ecd8457877b5ec636cb51 100755 (executable)
--- a/gitweb.cgi
+++ b/gitweb.cgi
@@ -39,12 +39,16 @@ my $home_link =             $my_uri;
 my $home_text =                "indextext.html";
 
 # URI of default stylesheet
-my $stylesheet =       "gitweb.css";
+my $stylesheet =       "gitweb.css";
 
 # source of projects list
 #my $projects_list =   $projectroot;
 my $projects_list =    "index/index.aux";
 
+# default blob_plain mimetype and default charset for text/plain blob
+my $default_blob_plain_mimetype = 'text/plain';
+my $default_text_plain_charset  = 'utf-8';     # can be undefined
+
 # input validation and dispatch
 my $action = $cgi->param('a');
 if (defined $action) {
@@ -1482,15 +1486,46 @@ sub git_blob {
        git_footer_html();
 }
 
+sub git_blob_plain_mimetype {
+       my $fd = shift;
+       my $filename = shift;
+
+       # just in case
+       return $default_blob_plain_mimetype unless $fd;
+
+       if (-T $fd) {
+               return 'text/plain' .
+                      ($default_text_plain_charset ? '; charset='.$default_text_plain_charset : '');
+       } elsif (! $filename) {
+               return 'application/octet-stream';
+       } elsif ($filename =~ m/\.png$/i) {
+               return 'image/png';
+       } elsif ($filename =~ m/\.gif$/i) {
+               return 'image/gif';
+       } elsif ($filename =~ m/\.jpe?g$/i) {
+               return 'image/jpeg';
+       } else {
+               return 'application/octet-stream';
+       }
+}
+
 sub git_blob_plain {
-       my $save_as = "$hash.txt";
+       open my $fd, "-|", "$gitbin/git-cat-file blob $hash" or return;
+       my $type = git_blob_plain_mimetype($fd, $file_name);
+
+       # save as filename, even when no $file_name is given
+       my $save_as = "$hash";
        if (defined $file_name) {
                $save_as = $file_name;
+       } elsif ($type =~ m/^text\//) {
+               $save_as .= '.txt';
        }
-       print $cgi->header(-type => "text/plain", -charset => 'utf-8', '-content-disposition' => "inline; filename=\"$save_as\"");
-       open my $fd, "-|", "$gitbin/git-cat-file blob $hash" or return;
+
+       print $cgi->header(-type => "$type", '-content-disposition' => "inline; filename=\"$save_as\"");
        undef $/;
+       binmode STDOUT, ':raw' unless $type =~ m/^text\//;
        print <$fd>;
+       binmode STDOUT, ':utf8' unless $type =~ m/^text\//;
        $/ = "\n";
        close $fd;
 }