#! /usr/bin/perl -w use 5.014; use feature 'unicode_strings'; use strict; use warnings; use Unicode::Normalize; my $string = "\x{c3}\x{a9}"; my $decomposed = NFD( $string ); $decomposed =~ s/\pM//g; $decomposed = NFC( $decomposed ); print length($decomposed)."\n"; print "$decomposed\n"; ------------------ ~# ./test.pl 2 A?