#!/usr/bin/perl use open IO => ':utf8'; while(<>) { chomp; ($nonenglish = $_) =~ s/[A-Za-z]//g; print length($nonenglish), " $nonenglish\n"; } #### $ perl nonenglish.pl æ 2 æ ꝥ 3 ꝥ 𪛖 4 𪛖 ^D $