#!/usr/bin/perl -w
use strict;
use Getopt::Long;

GetOptions(
    'lines|n:i' => \my $lines,
    'column|c:i' => \my $column,
    'sep|s:s' => \my $separator,
    'transform|f:s' => \my $transform,
    'max|m' => \my $maximum_only,
);
$lines ||= 10000;
$column ||= 1;
$separator ||= ";"; # should from the input, but...

$column--; # adjust from human to Perl

my %vals;
my @F;
my $line=0;

sub transform{ $_[0] };

if ($transform) {
    no warnings 'redefine';
    eval <<CODE
sub transform { $transform(\$_[0]) };
CODE
};

FILE: for my $file (@ARGV) {
    my $fh;
    if ($file =~ /\.gz|\.ebcdic/) {
        open $fh, '-|', 'gzcat', $file
            or die "Couldn't open '$file': $!";
    } else {
        open $fh, '<', $file
            or die "Couldn't open '$file': $!";
    };
    while (<$fh>) {
        @F = split /$separator/o;
        $vals{ transform($F[ $column ])}++;

        last FILE if $lines <= $line++;
    };
};

for (sort { $vals{$b} <=> $vals{$a} } keys %vals) {
    if ($maximum_only) {
        if ($vals{$_} / $lines > 0.6) {
            print "$_\n";
            last
        } else {
            die "No confidence in '$_': Only $vals{$_} out of $lines values match\n";
        };
    } else {
        print "$_: $vals{$_}\n";
    };
};