#!/usr/bin/perl
use warnings;
use strict;

my $infile = $ARGV[0];

print "List of entities in ", $infile, "\n";

#define regexes as search target (in the array @regexes)
my $regex = qr/(&[^;]+;)/;

open my $in, '<', $infile or die "Cannot open $infile for reading: $!";

#read input file in variable $xml
my $xml;
{
  local $/ = undef;
  $xml = <$in>;
}

#define output file
open my $out, '>', 'ent-list.txt' or die $!;

#output list of entities
print {$out} "$1\n" while $xml =~ /$regex/g;
 
close $in;
close $out;