my $open_mode = "<:utf8"; # or "<:encoding(UTF-16LE)" etc.
open( IN, $open_mode, "unicode_input.txt" );

binmode( STDOUT, ":utf8" ); # or whatever form of unicode is supported by your display tool

while (<IN>) {  # data will be read as (or converted to) utf8 on input
   # do stuff with $_, then
   print;
}

##</code><code>##

my %charpinyin;

while (<IN>) {
   chomp;
   my ( $chchar, $pinyin ) = split /\t/;
   $charpinyin{$chchar} = $pinyin;
}