use warnings; use strict; use Test::More tests=>12; my $in = "\N{U+CF} \N{U+2764} \N{U+1F42A}"; is utf8cut($in, 11), "\N{U+CF} \N{U+2764} \N{U+1F42A}"; is utf8cut($in, $_), "\N{U+CF} \N{U+2764} " for 10,9,8,7; is utf8cut($in, 6), "\N{U+CF} \N{U+2764}"; is utf8cut($in, $_), "\N{U+CF} " for 5,4,3; is utf8cut($in, 2), "\N{U+CF}"; is utf8cut($in, $_), "" for 1,0; sub utf8cut { my ($str, $bytelen) = @_; utf8::encode($str); $str = substr $str, 0, $bytelen; $str =~ s/(?: [\xC0-\xDF] | [\xE0-\xEF] [\x80-\xBF]? | [\xF0-\xF7] [\x80-\xBF]{0,2} )\z//x; utf8::decode($str); return $str; }