#this will be used just for the first run
#!/usr/bin/perl 
use strict;
use warnings;
use File::Find;
use YAML qw/LoadFile/;
use Data::Dumper;
use Digest::SHA1 qw/sha1_hex/;
use DBI;
use DateTime;

my $dbh = DBI->connect("dbi:SQLite:dbname=checksum_db.sqlite","","");

my $config_path = 'config.yml';
my $config = LoadFile($config_path);

#to add columns in db for link,dir,file to know what the name column stands for...
sub add_to_db {
	my ($checksum,$last_modif_time,$size,$name)=@_;
	#maybe calculating is_* should be done in process_file
	my $is_dir  = (-d $name)?'Y':'N';
	my $is_file = (-f $name)?'Y':'N';
	my $is_link = (-l $name)?'Y':'N';
	$dbh->do(
		sprintf "INSERT INTO checksums (checksum,size,last_date_modified,name,is_dir,is_file,is_link) VALUES (\"%s\",\"%s\",\"%s\",\"%s\",\"%s\",\"%s\",\"%s\");",
		$checksum,
		$size,
		$last_modif_time->ymd,
		$name,
		$is_dir,
		$is_file,
		$is_link
	);
};

sub delete_from_db {#remains to be completed
	my ($name)=@_;
};


sub file2sha1 {
	my $file=$_[0];
	return '' if -d $file; #have to find out if to prune when a directory is found that doesn't match the regex
	open my $f,"<$file";
	my $sha1 = Digest::SHA1->new;
	$sha1->addfile(*$f);
	return $sha1->hexdigest;
}


sub process_file {
	my $dir_configs=$_[0];
	##optimisation using -d -l -f -s just once for return and also for adding

	#if current "file"(unix terminology) is a directory and the yaml configuration
	#tells us to eliminate directories from the search we do so by returning from the
	#callback
	return if -d $File::Find::name && ! $dir_configs->{dir};
	return if -l $File::Find::name && ! $dir_configs->{link};
	return if -f $File::Find::name && ! $dir_configs->{file};
	return if -s $File::Find::name < $config->{minsize};
	unless($File::Find::name =~  /$dir_configs->{regex}/) {
		if(-d $File::Find::name) {
			$File::Find::prune=1;
		}
		return;
	}

	my ($dev,$ino,$mode,$nlink,$uid,$gid,$rdev,$size,
		$atime,$mtime,$ctime,$blksize,$blocks)
	= stat($File::Find::name);
	my $last_modif_time=DateTime->from_epoch(epoch=>$mtime);
#	printf "%s %s %s %s\n",
#	$File::Find::name,
#	file2sha1($File::Find::name),
#	-s $File::Find::name,
#	$last_modif_time;

	add_to_db(file2sha1($File::Find::name),$last_modif_time,-s $File::Find::name,$File::Find::name);
	#print Dumper $dir_configs;
};


for my $searched_dir_hash (@{ $config->{directories} }) {
	# we skip the entry if it does not exist or it is not a directory
	next unless (-e $searched_dir_hash->{path} && -d $searched_dir_hash->{path}); 
	#we pass to the process_file function the yml configuration for the current directory that is searched
	find(
		{  wanted=> sub { process_file($searched_dir_hash);}  }, 
		$searched_dir_hash->{path} 
	);
}