#!/usr/local/bin/perl -w
use strict;        ## use strict, use strict, use strict!!!
$|++;              ## enable line buffering to STDOUT

use FileHandle; 

# A program that accept an input file: Scorpion database from Gen Bank
# and will output the database in BioWare format

## used descriptive variable names
## used shift operator to process arguments (shift) and die with usage
my $infile = shift || die "usage: $0 infile outfile\n";
my $outfile = shift || die "usage: $0 infile outfile\n";
my $item_count=1;
my $item='D000001';
my $IN = new FileHandle;
my $OUT = new FileHandle;

## check status of open and print $! for descriptive error message
open($IN, "< " . $infile) or die "Can't open $infile. $!";
open($OUT, "> " . $outfile) or die "Can't open $outfile. $!";

while(<$IN>) {
	## remove trailing newline
	chomp;
	## skip blank lines
	next if( '^\s*$' );
	## print newline if end of record
	if( '^//$' ) { print $OUT "\n"; next; }

	## expects date format like 1or2-three-four characters (perlre)
	if( /^DATE\s+(..?)-(...)-(....)$/ ) { ## very fast regex
		print $OUT "DBACC\t", $item++, "\n";
		print $OUT "DATE\t\"$1-$2 $3\"\n";
	} 
	## non-greedy match between double quotes (perlre)
	elsif( /^\s*\/exon="(.*?)"$/ ) { 
		## handle null case
		print $OUT "Exon\t{Translation -}\n" unless $1;
		## seperate the matched string and process each (split)
		for(split ';', $1) {
			print $OUT "Exon\t{Translation\%", $_ ,"}\n";
		}
	}
	## non-greedy match between double quotes (perlre)
	elsif( /^\s*\/intron="(.*?)"$/ ) {
		## handle null case
		print $OUT "Intron\t{Translation -}\n" unless $1;
		## seperate the matched string and process each
		for(split ';', $1) {
			print $OUT "Intron\t{Translation\%", $_ ,"}\n";
		}
	}
}
## check status of close and print $! for descriptive error message
close($IN) or die "Can't close $infile. $!";
close($OUT) or die "Can't close $outfile. $!";