gitweb: Syntax highlighting support

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index 9d4c58238ea87963221d948020e928d232c0d90d..de18ebf30195f43082f80e2f76dc20c0b8c061dd 100755 (executable)
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -227,6 +227,36 @@ BEGIN
 # Leave it undefined (or set to 'undef') to turn off load checking.
 our $maxload = 300;
 
+# syntax highlighting
+our %highlight_type = (
+       # match by basename
+       'SConstruct' => 'py',
+       'Program' => 'py',
+       'Library' => 'py',
+       'Makefile' => 'make',
+       # match by extension
+       '\.py$' => 'py', # Python
+       '\.c$' => 'c',
+       '\.h$' => 'c',
+       '\.cpp$' => 'cpp',
+       '\.cxx$' => 'cpp',
+       '\.rb$' => 'ruby',
+       '\.java$' => 'java',
+       '\.css$' => 'css',
+       '\.php3?$' => 'php',
+       '\.sh$' => 'sh', # Bash / shell script
+       '\.pl$' => 'pl', # Perl
+       '\.js$' => 'js', # JavaScript
+       '\.tex$' => 'tex', # TeX and LaTeX
+       '\.bib$' => 'bib', # BibTeX
+       '\.x?html$' => 'xml',
+       '\.xml$' => 'xml',
+       '\.awk$' => 'awk',
+       '\.bat$' => 'bat', # DOS Batch script
+       '\.ini$' => 'ini',
+       '\.spec$' => 'spec', # RPM Spec
+);
+
 # You define site-wide feature defaults here; override them with
 # $GITWEB_CONFIG as necessary.
 our %feature = (
@@ -445,6 +475,19 @@ BEGIN
        'javascript-actions' => {
                'override' => 0,
                'default' => [0]},
+
+       # Syntax highlighting support. This is based on Daniel Svensson's
+       # and Sham Chukoury's work in gitweb-xmms2.git.
+       # It requires the 'highlight' program, and therefore is disabled
+       # by default.
+
+       # To enable system wide have in $GITWEB_CONFIG
+       # $feature{'highlight'}{'default'} = [1];
+
+       'highlight' => {
+               'sub' => sub { feature_bool('highlight', @_) },
+               'override' => 0,
+               'default' => [0]},
 );
 
 sub gitweb_get_feature {
@@ -1150,6 +1193,7 @@ sub validate_refname {
 # in utf-8 thanks to "binmode STDOUT, ':utf8'" at beginning
 sub to_utf8 {
        my $str = shift;
+       return undef unless defined $str;
        if (utf8::valid($str)) {
                utf8::decode($str);
                return $str;
@@ -1162,6 +1206,7 @@ sub to_utf8 {
 # correct, but quoted slashes look too horrible in bookmarks
 sub esc_param {
        my $str = shift;
+       return undef unless defined $str;
        $str =~ s/([^A-Za-z0-9\-_.~()\/:@ ]+)/CGI::escape($1)/eg;
        $str =~ s/ /\+/g;
        return $str;
@@ -1170,6 +1215,7 @@ sub esc_param {
 # quote unsafe chars in whole URL, so some charactrs cannot be quoted
 sub esc_url {
        my $str = shift;
+       return undef unless defined $str;
        $str =~ s/([^A-Za-z0-9\-_.~();\/;?:@&=])/sprintf("%%%02X", ord($1))/eg;
        $str =~ s/\+/%2B/g;
        $str =~ s/ /\+/g;
@@ -1181,6 +1227,8 @@ sub esc_html {
        my $str = shift;
        my %opts = @_;
 
+       return undef unless defined $str;
+
        $str = to_utf8($str);
        $str = $cgi->escapeHTML($str);
        if ($opts{'-nbsp'}) {
@@ -1195,6 +1243,8 @@ sub esc_path {
        my $str = shift;
        my %opts = @_;
 
+       return undef unless defined $str;
+
        $str = to_utf8($str);
        $str = $cgi->escapeHTML($str);
        if ($opts{'-nbsp'}) {
@@ -3381,7 +3431,7 @@ sub git_footer_html {
              "</html>";
 }
 
-# die_error(<http_status_code>, <error_message>)
+# die_error(<http_status_code>, <error_message>[, <detailed_html_description>])
 # Example: die_error(404, 'Hash not found')
 # By convention, use the following status codes (as defined in RFC 2616):
 # 400: Invalid or missing CGI parameters, or
@@ -3396,7 +3446,7 @@ sub git_footer_html {
 #      or down for maintenance).  Generally, this is a temporary state.
 sub die_error {
        my $status = shift || 500;
-       my $error = shift || "Internal server error";
+       my $error = esc_html(shift) || "Internal Server Error";
        my $extra = shift;
 
        my %http_responses = (
@@ -5339,6 +5389,7 @@ sub git_blob {
        open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash
                or die_error(500, "Couldn't cat $file_name, $hash");
        my $mimetype = blob_mimetype($fd, $file_name);
+       # use 'blob_plain' (aka 'raw') view for files that cannot be displayed
        if ($mimetype !~ m!^(?:text/|image/(?:gif|png|jpeg)$)! && -B $fd) {
                close $fd;
                return git_blob_plain($mimetype);
@@ -5346,6 +5397,25 @@ sub git_blob {
        # we can have blame only for text/* mimetype
        $have_blame &&= ($mimetype =~ m!^text/!);
 
+       my $have_highlight = gitweb_check_feature('highlight');
+       my $syntax;
+       if ($have_highlight && defined($file_name)) {
+               my $basename = basename($file_name, '.in');
+               foreach my $regexp (keys %highlight_type) {
+                       if ($basename =~ /$regexp/) {
+                               $syntax = $highlight_type{$regexp};
+                               last;
+                       }
+               }
+
+               if ($syntax) {
+                       close $fd;
+                       open $fd, quote_command(git_cmd(), "cat-file", "blob", $hash)." | ".
+                                 "highlight --xhtml --fragment -t 8 --syntax $syntax |"
+                               or die_error(500, "Couldn't open file or run syntax highlighter");
+               }
+       }
+
        git_header_html(undef, $expires);
        my $formats_nav = '';
        if (defined $hash_base && (my %co = parse_commit($hash_base))) {
@@ -5397,7 +5467,7 @@ sub git_blob {
                        $line = untabify($line);
                        printf "<div class=\"pre\"><a id=\"l%i\" href=\"" . href(-replay => 1)
                                . "#l%i\" class=\"linenr\">%4i</a> %s</div>\n",
-                              $nr, $nr, $nr, esc_html($line, -nbsp=>1);
+                              $nr, $nr, $nr, $syntax ? $line : esc_html($line, -nbsp=>1);
                }
        }
        close $fd