####################################################################
##                               MAIN
####################################################################

print "Reading a file...\n";

my $file = get_file('pdb244l.ent'); #execute get_file subroutine for a given input file
                                    #and store the data within $file

print "Parsing a file...\n";

my %record_types = parse_pdb_file($file);

print "Getting data...\n";

$record_types{'HELIX'} ? my %helix = get_helix($record_types{'HELIX'}) : ();

$record_types{'SHEET'} ? my %sheet = get_sheet($record_types{'SHEET'}) : ();

$record_types{'TURN'}  ? my %turn  = get_turn($record_types{'TURN'})  : ();

my %chains = extractSEQRES($record_types{'SEQRES'});

exit;

####################################################################
##                               SUBS
####################################################################

sub get_file { #to read from a file

  my ($input_file) = @_;
  
  open (IN, $input_file) || die "Cannot open $input_file for reading: $OS_ERROR\n"; #open a filehandle or die  
  
  my $sequence = ''; 
  
  foreach my $line (<IN>) { #for each line in the filehandle IN

    $sequence .= $line # add (concatenate) to a string sequence 
      
  }
  
  return $sequence; #return the string sequence
  
  close (IN);

}

sub parse_pdb_file { #to return a hash with keys that are record type names and 
                     #values that are scalar containing lines for that record type
  
  my @file = @_;

  my %record_types = ();
  
  foreach my $line (@file) {
    
    my ($record_type) = ($line =~ /^(\S+)/); #the pattern (\S+) is returned and saved in $recordtype
    
    if (defined $record_types{$record_type} ) {
      
      $record_types{$record_type} .= $line;
      
    } else {
      
      $record_types{$record_type} = $line; #.= fails if a key is undefined
      
    }
    
  }
  
  return %record_types;
  
}

sub get_helix { #to return a scalar containing H if given a scalar contains HELIX line

  my($helix) = @_;

  my @record = split ( /\n/, $helix);
  
  my %chain_hash = ();
  
  foreach my $line (@record) {
    
    my($this_chain) = stripspaces(substr($line, 19, 1));
    
    my($start) = stripspaces(substr($line, 21, 4));
    
    my($length) = stripspaces(substr($line, 71, 5));
    
    if (defined $chain_hash{$this_chain}) {
      
      $chain_hash{$this_chain} .= ':' . 'H' x $length . ";$start";
      
    } else {
      
      $chain_hash{$this_chain} = 'H' x $length . ";$start";
      
    }
  
  }
  
  return %chain_hash;

}

sub get_sheet  { #to return a scalar containing H if given a scalar contains SHEET line

  my($sheet) = @_;
  
  my @record = split ( /\n/, $sheet);
  
  my %chain_hash = ();
  
  foreach my $line (@record) {
    
    my($this_chain) = stripspaces(substr($line, 21, 1));
    
    my($start) = stripspaces(substr($line, 22, 4));
    
    my($end) = stripspaces(substr($line, 33, 4));

    my($length)	= $end - $start + 1;
    
    if (defined $chain_hash{$this_chain}) {
	 
      $chain_hash{$this_chain} .= ':' . 'S' x $length . ";$start";

    } else {
	   
      $chain_hash{$this_chain} = 'S' x $length . ";$start";

    }
   
  }

  return %chain_hash;

}

sub get_turn { #to return a scalar containing H if given a scalar contains TURN line

  my($turn) = @_;

  my @record = split ( /\n/, $turn);

  my %chain_hash = ();
    
  foreach my $line (@record) {
   
    my($this_chain) = stripspaces(substr($line, 19, 1));
    
    my($start) = stripspaces(substr($line, 20, 4));
    
    my($end) = stripspaces(substr($line, 31, 4));

    my($length)	= $end - $start + 1;
    
    if (defined $chain_hash{$this_chain}) {

      $chain_hash{$this_chain} .= ':' . 'T' x $length . ";$start";

    } else {
	   
      $chain_hash{$this_chain} = 'T' x $length . ";$start";

    }
   
  }

  return %chain_hash;

}

sub stripspaces { #to remove leading and trailing spaces

  my($string) = @_;

  $string =~ s/^\s*//;

  $string =~ s/\s*$//;

  return $string;

}

sub extractSEQRES {
  
  my ($seqres) = @_;
  
  my $lastchain;
  
  my $sequence = '';
  
  my %results = ();
  
  my @record = split(/\n/, $seqres);
  
  foreach my $line (@record) {
    
    my ($thischain) = stripspaces(substr($line, 11, 1));
    
    my ($residues)  = substr($line, 19, 52);    
    
    if (not defined $lastchain) {
      
      $sequence = $residues;
      
    } elsif ("$thischain" eq "$lastchain") {
      
      $sequence .= $residues;
      
    } elsif ($sequence) {
      
      $results{$lastchain} = $sequence;
      
      $sequence = $residues;
      
    }
    
    $lastchain = $thischain;
    
  }
  
  $results{$lastchain} = $sequence;
  
  return %results;
  
}