use Data::Dumper;

my (%symbol,@old,@new);
my $max          = 10;
my $ws_replace   = '_';
my $letters_only = 1;

while (<DATA>) {
   chomp;
   push @old, $_;
   $_ = substr $_,0,10 if $max;
   s/\s+/$ws_replace/g if $ws_replace;
   s/\W+//g            if $letters_only;
   $_ .= $.            if $symbol{$_}++;
   push @new, $_;
}

print Dumper \@old, \@new;

my %compare;
@compare{@old} = @new;

print Dumper \@compare;

__DATA__
Line one
Line two
xxxxxxxxxxx
Another line
xxxxxxxxxxx
Lines end here not
xxxxxxxxxxx
Fourth line (used to be)
Line five
Lines end here
Lines end here too