#!/usr/bin/perl -w

# Command line usage: perl<space>ESTNameConversion<space>input_file<space>output_file<space>user_defined_extension<return>
# This script takes the EST entries extracted from NCBI website in FASTA format as input;
# searches the description line for specific string of "ESTxxxx" (xxxx is a number);
# keeps only "ESTxxxx" as the entry name;
# and adds user-given extension name to the end of the entry names in the format of "EntryName.UserGivenExtension".
# This script is used to make EST sequences from different organisms distinguishable just by name.

my @seqs;
my $answer;

open INPUT, "$ARGV[0]"
    or die "Can't open input file: $!";

while (<INPUT>) {
    chomp;
    if ($_ =~ /^>/) {
	$_ =~ s/^(>).*(EST\d+).*$/$1$2/;
	if (defined ($ARGV[2])) {
	    $_ .= $ARGV[2];
	}
    }
    push @seqs, $_;
}

close INPUT
    or die "Can't close input file: $!";

# Check whether the output file is already existed.
# If so, don't overwrite it.

if (-e $ARGV[1]) {
    while (1) {
	print "Output file existed, overwrite? yes or no: \n";
	chomp ($answer = <STDIN>);
	if ($answer ne "yes" && $answer ne "no") {
	    print "Please answer yes or no!!! \n";
	    next;
	} else {
	    last;
	}
    }
} else {
    $answer = "yes";
}

if ($answer eq "no") {
    print "QUIT without overwriting existed output file!\n";
    exit;
} else {

# Write to the output file.
    open (OUTPUT, ">$ARGV[1]")
	or die "Can't open output file: $!";

    foreach (@seqs) {
	print OUTPUT "$_\n";
    }
}