use Unicode::UCD 'charinfo';

  # Look for codepoints not in Basic Latin 
  while ( $string  =~ s/(\P{InBasic_Latin})// ) {     
        my $U_char = $1;                              
          # e.g. U_char = ü  
        my $U_codepoint = ord($U_char);               
          # so U_codepoint = ord(ü)  = 252
        $string =~ s/$U_char/$subs{$U_codepoint}/;    
          # and $subs{252} = ü
  }