#!/usr/local/bin/perl -w

use strict;

## Prepare BLAST database
my $dir = ".\db";
opendir(DIR0, $dir) or die "Can't open $dir: $!\n";
while (defined(my $file = readdir(DIR0))) {
#用后缀找文件，next unless这样就可以在同一个目录下的不同后缀了。
	next unless $file =~ /\.faa$/;
#-pT处理蛋白
	print `formatdb -i $file -p T -o T`;
}

## Prepare .fna file
my $dir1 = ".\nt";
opendir(DIR1, $dir) or die "Can't open $dir: $!\n";
while (defined(my $file = readdir(DIR1))) {
	next unless $file =~ /\.fna$/;
#processed什么意思？连接文件名？
	my $processed_fna_file = join '.', $file, "processed";
	open (FNA, $file) or die "Can't open $file: $!\n";
	open (NEW, ">$processed_fna_file") or die "Can't open $processed_fna_file: $!\n";
#打开的文件不是零就处理。
	while (<FNA>) {
		chomp;
		next if /\>gi/;
		print NEW;
#添加新来的文件，但是为什么要去掉回车，会不会形成新的虚拟片段？
	}
	print "\n";
}

## Prepare .gbk file
my $dir2 = ".\all";
opendir(DIR2, $dir) or die "Can't open $dir: $!\n";
my $sep = '*'x80;
while (defined(my $file = readdir(DIR2))) {
	next unless $file =~ /\.gbk$/;
	my $processed_gbk_file = join '.', $file, "processed";
	open (GBK, $file) or die "Can't open $file: $!\n";
	open (NEW, ">$processed_gbk_file") or die "Can't open $processed_gbk_file: $!\n";
#模式匹配，提取基因信息。
	while (<GBK>) {
		/\s+gene\s+\w*\(?(\d+)\.\.(\d+)/ && do { print NEW "\n$sep\n"; };
		print NEW ;
	}
}