#!/usr/bin/perl -w



use strict;

# Set to filename of CSV file
my $csvfile = '';

# Set to filename of new file(file without duplicates)

my $newfile = '';

# Set to 1 if first line of CSV file contains field names, 0 otherwise
my $fieldnames = 1;

### Shouldn't need to change stuff below here ###

open (IN, "<$csvfile")  or die "Couldn't open input CSV file: $!";

open (OUT, ">$newfile") or die "Couldn't open output file: $!";

# Read header lines if they exist
my $header;
$header = <IN> if $fieldnames;

# Slurp in & sort everything else

my @data = sort <IN>;

# If we read in a header line, throw it back out again
print OUT $header;

my $n = 0;
# Now go through the data line by line, writing it to output unless


# to the previous line (in which case it's a dupe)
my $lastline = '';
foreach my $currentline (@data) {
  next if $currentline eq $lastline;
  print OUT $currentline;
  $lastline = $currentline;

  $n++;
}

close IN; close OUT;

print "Processing complete. In = " . scalar @data . " records, Out =
$n records\n";