Merge branch 'jk/colors'

"diff-highlight" (in contrib/) used to show byte-by-byte
differences, which meant that multi-byte characters can be chopped
in the middle.  It learned to pay attention to character boundaries
(assuming the UTF-8 payload).

* jk/colors:
  diff-highlight: do not split multibyte characters

1 files changed, 7 insertions, 2 deletions

diff --git a/contrib/diff-highlight/diff-highlight b/contrib/diff-highlight/diff-highlight
index 08c88bbc87..ffefc31a98 100755
--- a/contrib/diff-highlight/diff-highlight
+++ b/contrib/diff-highlight/diff-highlight
@@ -1,5 +1,6 @@
 #!/usr/bin/perl
 
+use 5.008;
 use warnings FATAL => 'all';
 use strict;
 
@@ -164,8 +165,12 @@ sub highlight_pair {
 
 sub split_line {
 	local $_ = shift;
-	return map { /$COLOR/ ? $_ : (split //) }
-	       split /($COLOR*)/;
+	return utf8::decode($_) ?
+		map { utf8::encode($_); $_ }
+			map { /$COLOR/ ? $_ : (split //) }
+			split /($COLOR+)/ :
+		map { /$COLOR/ ? $_ : (split //) }
+		split /($COLOR+)/;
 }
 
 sub highlight_line {