#!/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;


##</code><code>##

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

my $infile = $ARGV[0];
my $outfile = $ARGV[1];   

open(IN, '<' . $infile) or die "Cannot open $infile for reading: $!";
open(OUT, '>' . $outfile) or die $!;
chomp(my @matches = <IN>);

my %freq;
$freq{$_}++ for @matches;

print OUT "Statistics of entities in '", $infile, "'\n=================================================\n";
for my $entity (sort keys %freq) {    
    printf OUT "%-20s %10s \n", $entity, $freq{$entity};
}