while(<INFILE>){
   
    #print "here\n";
    
    if ($_ =~ /^(.{1,50})\t{0,50}(.{0,50})\t{0,1}(.{0,50})\t{0,1}(.{0,
+50})\t{0,1}(.{0,50})\t{0,1}(.{0,50})\t{0,1}(.{0,50})\t{0,1}(.{0,50})\
+t{0,1}(.{0,50})/){
    
    #print "here_B\n";
    
    $bumb = "";

    $gene_id = $1;
    if ($2 =~ /.{1,50}/){ push (@alternative_ids, $2)}
    else{
       push (@alternative_ids, $bumb); 
    }
    
    if ($3 =~ /.{1,50}/){ push (@alternative_ids, $3)}
    else{
        push (@alternative_ids, $bumb);
    }
    
    if ($4 =~ /.{1,50}/){ push (@alternative_ids, $4)}
    else{
        push (@alternative_ids, $bumb);
    }
    
    if ($5 =~ /.{1,50}/){ push (@alternative_ids, $5)}
    else{
        push (@alternative_ids, $bumb);
    }
    
    if ($6 =~ /.{1,50}/){ push (@alternative_ids, $6)}
    else{
        push (@alternative_ids, $bumb);
    }

    if ($7 =~ /.{1,50}/){ push (@alternative_ids, $7)}
    else{
        push (@alternative_ids, $bumb);
    }
    
    if ($8 =~ /.{1,50}/){ push (@alternative_ids, $8)}
           else{
        push (@alternative_ids, $bumb);
    }
    
    if ($9 =~ /.{1,50}/){ push (@alternative_ids, $9)}
    else{
        push (@alternative_ids, $bumb);
    }




    print @alternative_id; 

    foreach (@alternative_ids){
        
        $old_line = $new_line;
        $alternative_id = $_;
        
        $new_line = "$gene_id\t$alternative_id\n"; 
        
        @record_previous_lines = qw/blank/;

        if ($new_line ne $old_line){ #discount consecutive repeats of 
+identical lines
            $switch = 1;

        foreach(@record_previous_lines){
          
            if ($_ =~ /$new_line.$old_line/){
            $switch = 2;
            }
        }
        
        if ($switch = 1){ # don't print lines that have previously bee
+n repeated
            print OUT_B "$new_line$old_line";
        }
        
        if (@record_previous_lines > 200){ # don't let this array get 
+bigger than 200
            shift @record_previous_lines; # shift deletes the first va
+lue of an array
        }
        push (@record_previous_lines, $new_line.$old_lines);
        }
    }
    undef @alternative_ids;
    }
}
[download]

In

      if ($switch = 1){ # don't print lines that have previously been 
+repeated
           print OUT_B "$new_line$old_line";
       }
[download]

should that not be

      if ($switch== 1)

CountZero

"If you have four groups working on a compiler, you'll get a 4-pass compiler." - Conway's Law

OK well if you had said "I expect to find duplicate lines within 200 lines of the original" then we could have helped you sooner!

:)

So ... how do you want that "last bit" to work, and how is it really working?

It doen't seem to go to $switch = 2 . Even when I remove the . in the regexp of that loop.

how clustered are your lines? here are a couple tweakable previous line recognizers.

#
# remember everything, probably uses too much memory.
#
{
    my %seen;
    sub seen_complete {
        return 1 if exists $seen{$_[0]};
        $seen{$_[0]} = ();
        return 0;
    }
}

#
# remember last N lines only.
#
{
    my %seen;
    my $remember = 200;
    my @memory;
    sub seen_fixed {
        return 1 if exists $seen{$_[0]};
        delete $seen{shift(@memory)} if @memory > $remember;
        push @memory, $_[0];
        $seen{$_[0]} = ();
        return 0;
    }
}

#
# remember N buckets of lines with X lines per bucket.
#
{
    my @bucket = ( {} );
    my $numbuckets = 2;
    my $bucketsize = 200;
    sub seen_bucket {
        foreach (@bucket) {
            return 1 if exists $_->{$_[0]};
        }
        if (keys %{$bucket[-1]} >= $bucketsize) {
            shift @bucket if @bucket >= $numbuckets;
            push @bucket, {};
        }
        $bucket[-1]->{$_[0]} = ();
        return 0;
    }
}
[download]

i only tested the last one, and only sorta tested it at that.

while (<>) {
    print unless seen_bucket($_);
}
__END__

Ten sets of 1..400 should get uniq'd to 1..400

$ perl -le 'for(1..10){for(1..400){print}}' | perl dup.pl | wc -l
    400

Ten sets of 1..401 should get uniq'd to (1..401) x 10 because
2 buckets of 200 lines hold upto 400 

$ perl -le 'for(1..10){for(1..401){print}}' | perl dup.pl | wc -l
   4010
[download]