#!/usr/bin/perl -CS

use strict;

open(DB,"UnicodeData.txt") or die "UnicodeData.txt: $!";
my @lines = grep /^1E[A-F].;/, <DB>;
close DB;

# load the decomp hash: keys are unicode Vietnamese,
# values are two-character decompositions

my %decomp;
for ( @lines ) {
    my ($u,$d) = (split /;/, $_ )[0,5];
    my $uc = chr( hex( $u ));
    my $cc = join '', map { chr( hex( $_ )) } split / /,$d;
    $decomp{$uc} = $cc;
}

my $todecomp = join '', keys %decomp;
# now apply decomposition to data:

while (<>) {
    s/([$todecomp])/$decomp{$1}/g;
    print;
}