[PATCHv1 1/2] gitweb: Syntax highlighting support

[Jakub Narebski <jnareb@gmail.com>]

From: Johannes Schindelin <johannes.schindelin@gmx.de>

It requires the 'highlight' program to do all the heavy-lifting.

This is loosely based on Daniel Svensson's and Sham Chukoury's work in
gitweb-xmms2.git (it cannot be cherry-picked, as gitweb-xmms2 first forked
wildly, then not contributed back, and then went stale).

[jn: cherry picked from bc1ed6aafd9ee4937559535c66c8bddf1864bec6
 in http://repo.or.cz/w/git/dscho.git, with a few changes]

Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
Signed-off-by: Jakub Narebski <jnareb@gmail.com>
---
This patch is unchanged from previous version.


Compared to the version in Dscho repository, it makes gitweb do line
numbering by itself, instead of making 'highlight' do it... and then
rewriting it to conform to the rest of gitweb.  It also leaves tab
expansion to gitweb, for 'blob' view to look the same with and without
syntax highlighting enabled.

The list of supported extensions is widened, and syntax is decided
based on basename, not on whole pathname (which might be a mistake).
Also the '.in' suffix is stripped if it is present (so 'git.spec.in'
file would use 'spec' syntax).

Note that gitweb.css contains default 'highlight' style, but perhaps
other style would be better fit for default gitweb CSS.

 gitweb/gitweb.css  |   18 ++++++++++++++
 gitweb/gitweb.perl |   65 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 82 insertions(+), 1 deletions(-)

diff --git a/gitweb/gitweb.css b/gitweb/gitweb.css
index 50067f2..4132aab 100644
--- a/gitweb/gitweb.css
+++ b/gitweb/gitweb.css
@@ -572,3 +572,21 @@ span.match {
 div.binary {
 	font-style: italic;
 }
+
+/* Style definition generated by highlight 2.4.5, http://www.andre-simon.de/ */
+
+/* Highlighting theme definition: */
+
+.num    { color:#2928ff; }
+.esc    { color:#ff00ff; }
+.str    { color:#ff0000; }
+.dstr   { color:#818100; }
+.slc    { color:#838183; font-style:italic; }
+.com    { color:#838183; font-style:italic; }
+.dir    { color:#008200; }
+.sym    { color:#000000; }
+.line   { color:#555555; }
+.kwa    { color:#000000; font-weight:bold; }
+.kwb    { color:#830000; }
+.kwc    { color:#000000; font-weight:bold; }
+.kwd    { color:#010181; }
diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index c356e95..de18ebf 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -227,6 +227,36 @@ our %avatar_size = (
 # 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 @@ 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, 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 {
@@ -5346,6 +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);
@@ -5353,6 +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))) {
@@ -5404,7 +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
-- 
1.7.0.1