[PATCH] contrib/diff-highlight: multibyte characters diff
Signed-off-by: Yoshihiro Sugi <sugi1982@gmail.com>
diff-highlight split each hunks and compare them as byte sequences.
it causes problems when diff hunks include multibyte characters.
This change enable to work on such cases by decoding inputs and encoding output as utf8 string.
---
contrib/diff-highlight/diff-highlight | 16 ++++++++++------
1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/contrib/diff-highlight/diff-highlight b/contrib/diff-highlight/diff-highlight
index c4404d4..49b4f53 100755
--- a/contrib/diff-highlight/diff-highlight
+++ b/contrib/diff-highlight/diff-highlight
@@ -2,6 +2,7 @@
use warnings FATAL => 'all';
use strict;
+use Encode qw(decode_utf8 encode_utf8);
# Highlight by reversing foreground and background. You could do
# other things like bold or underline if you prefer.
@@ -15,8 +16,9 @@ my @added;
my $in_hunk;
while (<>) {
+ $_ = decode_utf8($_);
if (!$in_hunk) {
- print;
+ print encode_utf8($_);
$in_hunk = /^$COLOR*\@/;
}
elsif (/^$COLOR*-/) {
@@ -30,7 +32,7 @@ while (<>) {
@removed = ();
@added = ();
- print;
+ print encode_utf8($_);
$in_hunk = /^$COLOR*[\@ ]/;
}
@@ -58,7 +60,8 @@ sub show_hunk {
# If one side is empty, then there is nothing to compare or highlight.
if (!@$a || !@$b) {
- print @$a, @$b;
+ print encode_utf8($_) for @$a;
+ print encode_utf8($_) for @$b;
return;
}
@@ -67,17 +70,18 @@ sub show_hunk {
# stupid, and only handle multi-line hunks that remove and add the same
# number of lines.
if (@$a != @$b) {
- print @$a, @$b;
+ print encode_utf8($_) for @$a;
+ print encode_utf8($_) for @$b;
return;
}
my @queue;
for (my $i = 0; $i < @$a; $i++) {
my ($rm, $add) = highlight_pair($a->[$i], $b->[$i]);
- print $rm;
+ print encode_utf8($rm);
push @queue, $add;
}
- print @queue;
+ print encode_utf8($_) for @queue;
}
sub highlight_pair {
--
1.8.5.3