Merge branch 'jn/gitweb-syntax-highlight'

* jn/gitweb-syntax-highlight:
  gitweb: Refactor syntax highlighting support
  gitweb: Syntax highlighting support

1 files changed, 76 insertions, 3 deletions

diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index e108bbc60a..2365311d94 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -445,6 +445,19 @@ our %feature = (
 	'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 present in $PATH,
+	# 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 {
@@ -3179,6 +3192,61 @@ sub blob_contenttype {
 	return $type;
 }
 
+# guess file syntax for syntax highlighting; return undef if no highlighting
+# the name of syntax can (in the future) depend on syntax highlighter used
+sub guess_file_syntax {
+	my ($highlight, $mimetype, $file_name) = @_;
+	return undef unless ($highlight && defined $file_name);
+
+	# configuration for 'highlight' (http://www.andre-simon.de/)
+	# match by basename
+	my %highlight_basename = (
+		#'Program' => 'py',
+		#'Library' => 'py',
+		'SConstruct' => 'py', # SCons equivalent of Makefile
+		'Makefile' => 'make',
+	);
+	# match by extension
+	my %highlight_ext = (
+		# main extensions, defining name of syntax;
+		# see files in /usr/share/highlight/langDefs/ directory
+		map { $_ => $_ }
+			qw(py c cpp rb java css php sh pl js tex bib xml awk bat ini spec tcl),
+		# alternate extensions, see /etc/highlight/filetypes.conf
+		'h' => 'c',
+		map { $_ => 'cpp' } qw(cxx c++ cc),
+		map { $_ => 'php' } qw(php3 php4),
+		map { $_ => 'pl'  } qw(perl pm), # perhaps also 'cgi'
+		'mak' => 'make',
+		map { $_ => 'xml' } qw(xhtml html htm),
+	);
+
+	my $basename = basename($file_name, '.in');
+	return $highlight_basename{$basename}
+		if exists $highlight_basename{$basename};
+
+	$basename =~ /\.([^.]*)$/;
+	my $ext = $1 or return undef;
+	return $highlight_ext{$ext}
+		if exists $highlight_ext{$ext};
+
+	return undef;
+}
+
+# run highlighter and return FD of its output,
+# or return original FD if no highlighting
+sub run_highlighter {
+	my ($fd, $highlight, $syntax) = @_;
+	return $fd unless ($highlight && defined $syntax);
+
+	close $fd
+		or die_error(404, "Reading blob failed");
+	open $fd, quote_command(git_cmd(), "cat-file", "blob", $hash)." | ".
+	          "highlight --xhtml --fragment --syntax $syntax |"
+		or die_error(500, "Couldn't open file or run syntax highlighter");
+	return $fd;
+}
+
 ## ======================================================================
 ## functions printing HTML: header, footer, error page
 
@@ -5380,6 +5448,7 @@ 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);
@@ -5387,6 +5456,11 @@ sub git_blob {
 	# we can have blame only for text/* mimetype
 	$have_blame &&= ($mimetype =~ m!^text/!);
 
+	my $highlight = gitweb_check_feature('highlight');
+	my $syntax = guess_file_syntax($highlight, $mimetype, $file_name);
+	$fd = run_highlighter($fd, $highlight, $syntax)
+		if $syntax;
+
 	git_header_html(undef, $expires);
 	my $formats_nav = '';
 	if (defined $hash_base && (my %co = parse_commit($hash_base))) {
@@ -5436,9 +5510,8 @@ sub git_blob {
 			chomp $line;
 			$nr++;
 			$line = untabify($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);
+			printf qq!<div class="pre"><a id="l%i" href="%s#l%i" class="linenr">%4i</a> %s</div>\n!,
+			       $nr, href(-replay => 1), $nr, $nr, $syntax ? $line : esc_html($line, -nbsp=>1);
 		}
 	}
 	close $fd