From 8d00662d7d263448d90637ef6758fd2a0b526fec Mon Sep 17 00:00:00 2001 From: "Kyle J. McKay" Date: Fri, 3 Apr 2015 15:15:14 -0700 Subject: diff-highlight: do not split multibyte characters When the input is UTF-8 and Perl is operating on bytes instead of characters, a diff that changes one multibyte character to another that shares an initial byte sequence will result in a broken diff display as the common byte sequence prefix will be separated from the rest of the bytes in the multibyte character. For example, if a single line contains only the unicode character U+C9C4 (encoded as UTF-8 0xEC, 0xA7, 0x84) and that line is then changed to the unicode character U+C9C0 (encoded as UTF-8 0xEC, 0xA7, 0x80), when operating on bytes diff-highlight will show only the single byte change from 0x84 to 0x80 thus creating invalid UTF-8 and a broken diff display. Fix this by putting Perl into character mode when splitting the line and then back into byte mode after the split is finished. The utf8::xxx functions require Perl 5.8 so we require that as well. Also, since we are mucking with code in the split_line function, we change a '*' quantifier to a '+' quantifier when matching the $COLOR expression which has the side effect of speeding everything up while eliminating useless '' elements in the returned array. Reported-by: Yi EungJun Signed-off-by: Kyle J. McKay Acked-by: Jeff King Signed-off-by: Junio C Hamano --- contrib/diff-highlight/diff-highlight | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'contrib/diff-highlight') diff --git a/contrib/diff-highlight/diff-highlight b/contrib/diff-highlight/diff-highlight index 4a5f317b7c..54b359b7b7 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; @@ -160,8 +161,12 @@ 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 { -- cgit v1.2.3