From fdb7384d3d401cc9d6ece34a038e1b585712c512 Mon Sep 17 00:00:00 2001 From: Joel Barry Date: Wed, 27 Feb 2019 10:17:29 -0500 Subject: [PATCH] Fix non-ASCII lowercasing --- scripts/generic/multi-bleu-detok.perl | 3 +++ 1 file changed, 3 insertions(+) diff --git a/scripts/generic/multi-bleu-detok.perl b/scripts/generic/multi-bleu-detok.perl index d2ef60c90..e1f69501e 100755 --- a/scripts/generic/multi-bleu-detok.perl +++ b/scripts/generic/multi-bleu-detok.perl @@ -14,6 +14,9 @@ use warnings; use strict; +binmode(STDIN, ":utf8"); +use open ':encoding(UTF-8)'; + my $lowercase = 0; if ($ARGV[0] eq "-lc") { $lowercase = 1;