#!/usr/local/bin/gawk -f
#
# Gawk script that read and write ATOM records in pdb files
#
# Format descriprion of ATOM records: 
# from http://www.rcsb.org/pdb/docs/format/pdbguide2.2/guide2.2_frame.html
#
#COLUMNS        DATA TYPE       FIELD         DEFINITION
#---------------------------------------------------------------------------------
# 1 -  6        Record name     "ATOM  "
# 7 - 11        Integer         serial        Atom serial number.
#13 - 16        Atom            name          Atom name.
#17             Character       altLoc        Alternate location indicator.
#18 - 20        Residue name    resName       Residue name.
#22             Character       chainID       Chain identifier.
#23 - 26        Integer         resSeq        Residue sequence number.
#27             AChar           iCode         Code for insertion of residues.
#31 - 38        Real(8.3)       x             Orthogonal coordinates for X in
#39 - 46        Real(8.3)       y             Orthogonal coordinates for Y in
#47 - 54        Real(8.3)       z             Orthogonal coordinates for Z in
#55 - 60        Real(6.2)       occupancy     Occupancy.
#61 - 66        Real(6.2)       tempFactor    Temperature factor.
#73 - 76        LString(4)      segID         Segment identifier, left-justified.
#77 - 78        LString(2)      element       Element symbol, right-justified.
#79 - 80        LString(2)      charge        Charge on the atom.
#
#
#
{
  if (/^ATOM/){
    #
    # Get data from ATOM line
    #
    ATOM = substr($0,1,6);
    serial = substr($0,7,4);
    name = substr($0,13,4);
    altLoc = substr($0,17,1);
    resName = substr($0,18,3);
    chainID = substr($0,22,1);
    resSeq = substr($0,23,4);
    iCode = substr($0,27,1);
    x = substr($0,31,8)*1.0;
    y = substr($0,39,8)*1.0;
    z = substr($0,47,8)*1.0;
    occupancy = substr($0,55,6)*1.0;
    tempFactor = substr($0,61,6);
    segID = substr($0,73,4);
    element = substr($0,77,2);
    charge = substr($0,79,2);
    #
    # Print data from ATOM line
    #
    printf("%6s%5d %4s%1s%3s %s%4d%1s %8.3f%8.3f%8.3f%6.2f%6.2f%4s%2s%2s\n",
      ATOM, 
      serial, 
      name, 
      altLoc, 
      resName, 
      chainID, 
      resSeq, 
      iCode, 
      x, 
      y, 
      z, 
      occupancy, 
      tempFactor, 
      segID, 
      element, 
      charge)
  }
}