atom.java

A program to find frequent molecular substructures and discriminative fragments in a database of mol

/*----------------------------------------------------------------------
  File    : Atom.java
  Contents: Atom management for molecules
  Author  : Christian Borgelt
  History : 11.03.2002 file created
            13.03.2002 atom type definitions added
            14.03.2002 memory optimization added
            19.03.2002 bug in function sortBonds fixed
            22.03.2002 second constructor added
            28.03.2002 atom type changed to protected
            03.08.2003 ring flag evaluation added to function sortBonds
            20.07.2005 parameter 'masks' removed from sortBonds
            23.07.2005 sorting order of an atom's bonds inverted
            01.08.2005 label and corresponding mask removed
            08.05.2006 function sortBondsEx added
            12.05.2006 bond comparison in sortBonds simplified
            10.08.2006 charge coding changed, chain type added
            13.08.2006 insertion sort only for small bond arrays
----------------------------------------------------------------------*/
package moss;

import java.util.Comparator;
import java.util.Arrays;

/*--------------------------------------------------------------------*/
public class Atom {
/*--------------------------------------------------------------------*/

  /* --- constants: element types --- */
  public  static final int UNKNOWN       =  -1;
  public  static final int ANY           =   0;
  public  static final int HYDROGEN      =   1;  /* H  */
  public  static final int HELIUM        =   2;  /* He */
  public  static final int LITHIUM       =   3;  /* Li */
  public  static final int BERYLLIUM     =   4;  /* Be */
  public  static final int BORON         =   5;  /* B  */
  public  static final int CARBON        =   6;  /* C  */
  public  static final int NITROGEN      =   7;  /* N  */
  public  static final int OXYGEN        =   8;  /* O  */
  public  static final int FLOURINE      =   9;  /* F  */
  public  static final int NEON          =  10;  /* Ne */
  public  static final int SODIUM        =  11;  /* Na */
  public  static final int MAGNESIUM     =  12;  /* Mg */
  public  static final int ALUMINUM      =  13;  /* Al */
  public  static final int SILICON       =  14;  /* Si */
  public  static final int PHOSPHORUS    =  15;  /* P  */
  public  static final int SULFUR        =  16;  /* S  */
  public  static final int CHLORINE      =  17;  /* Cl */
  public  static final int ARGON         =  18;  /* Ar */
  public  static final int POTASSIUM     =  19;  /* K  */
  public  static final int CALCIUM       =  20;  /* Ca */
  public  static final int SCANDIUM      =  21;  /* Sc */
  public  static final int TITANIUM      =  22;  /* Ti */
  public  static final int VANADIUM      =  23;  /* V  */
  public  static final int CHROMIUM      =  24;  /* Cr */
  public  static final int MANGANESE     =  25;  /* Mn */
  public  static final int IRON          =  26;  /* Fe */
  public  static final int COBALT        =  27;  /* Co */
  public  static final int NICKEL        =  28;  /* Ni */
  public  static final int COPPER        =  29;  /* Cu */
  public  static final int ZINC          =  30;  /* Zn */
  public  static final int GALLIUM       =  31;  /* Ga */
  public  static final int GERMANIUM     =  32;  /* Ge */
  public  static final int ARSENIC       =  33;  /* As */
  public  static final int SELENIUM      =  34;  /* Se */
  public  static final int BROMINE       =  35;  /* Br */
  public  static final int KRYPTON       =  36;  /* Kr */
  public  static final int RUBIDIUM      =  37;  /* Rb */
  public  static final int STRONTIUM     =  38;  /* Sr */
  public  static final int YTTRIUM       =  39;  /* Y  */
  public  static final int ZIRCONIUM     =  40;  /* Zr */
  public  static final int NIOBIUM       =  41;  /* Nb */
  public  static final int MOLYBDENUM    =  42;  /* Mo */
  public  static final int TECHNETIUM    =  43;  /* Tc */
  public  static final int RUTHENIUM     =  44;  /* Ru */
  public  static final int RHODIUM       =  45;  /* Rh */
  public  static final int PALLADIUM     =  46;  /* Pd */
  public  static final int SILVER        =  47;  /* Ag */
  public  static final int CADMIUM       =  48;  /* Cd */
  public  static final int INDIUM        =  49;  /* In */
  public  static final int TIN           =  50;  /* Sn */
  public  static final int ANTIMONY      =  51;  /* Sb */
  public  static final int TELLURIUM     =  52;  /* Te */
  public  static final int IODINE        =  53;  /* I  */
  public  static final int XENON         =  54;  /* Xe */
  public  static final int CESIUM        =  55;  /* Cs */
  public  static final int BARIUM        =  56;  /* Ba */
  public  static final int LANTHANUM     =  57;  /* La */
  public  static final int CERIUM        =  58;  /* Ce */
  public  static final int PRASEODYMIUM  =  59;  /* Pr */
  public  static final int NEODYMIUM     =  60;  /* Nd */
  public  static final int PROMETHIUM    =  61;  /* Pm */
  public  static final int SAMARIUM      =  62;  /* Sm */
  public  static final int EUROPIUM      =  63;  /* Eu */
  public  static final int GADOLINIUM    =  64;  /* Gd */
  public  static final int TERBIUM       =  65;  /* Tb */
  public  static final int DYSPROSIUM    =  66;  /* Dy */
  public  static final int HOLMIUM       =  67;  /* Ho */
  public  static final int ERBIUM        =  68;  /* Er */
  public  static final int THULIUM       =  69;  /* Tm */
  public  static final int YTTERBIUM     =  70;  /* Yb */
  public  static final int LUTETIUM      =  71;  /* Lu */
  public  static final int HAFNIUM       =  72;  /* Hf */
  public  static final int TANTALUM      =  73;  /* Ta */
  public  static final int TUNGSTEN      =  74;  /* W  */
  public  static final int RHENIUM       =  75;  /* Re */
  public  static final int OSMIUM        =  76;  /* Os */
  public  static final int IRIDIUM       =  77;  /* Ir */
  public  static final int PLATINUM      =  78;  /* Pt */
  public  static final int GOLD          =  79;  /* Au */
  public  static final int MERCURY       =  80;  /* Hg */
  public  static final int THALLIUM      =  81;  /* Tl */
  public  static final int LEAD          =  82;  /* Pb */
  public  static final int BISMUTH       =  83;  /* Bi */
  public  static final int POLONIUM      =  84;  /* Po */
  public  static final int ASTATINE      =  85;  /* At */
  public  static final int RADON         =  86;  /* Rn */
  public  static final int FRANCIUM      =  87;  /* Fr */
  public  static final int RADIUM        =  88;  /* Ra */
  public  static final int ACTINIUM      =  89;  /* Ac */
  public  static final int THORIUM       =  90;  /* Th */
  public  static final int PROTACTINIUM  =  91;  /* Pa */
  public  static final int URANIUM       =  92;  /* U  */
  public  static final int NEPTUNIUM     =  93;  /* Np */
  public  static final int PLUTONIUM     =  94;  /* Pu */
  public  static final int AMERICUM      =  95;  /* Am */
  public  static final int CURIUM        =  96;  /* Cm */
  public  static final int BERKELIUM     =  97;  /* Bk */
  public  static final int CALIFORNIUM   =  98;  /* Cf */
  public  static final int EINSTEINIUM   =  99;  /* Es */
  public  static final int FERMIUM       = 100;  /* Fm */
  public  static final int MENDELEVIUM   = 101;  /* Md */
  public  static final int NOBELIUM      = 102;  /* No */
  public  static final int LAWRENCIUM    = 103;  /* Lr */
  public  static final int RUTHERFORDIUM = 104;  /* Rf */
  public  static final int DUBNIUM       = 105;  /* Db */
  public  static final int SEABORGIUM    = 106;  /* Sg */
  public  static final int BOHRIUM       = 107;  /* Bh */
  public  static final int HASSIUM       = 108;  /* Hs */
  public  static final int MEITNERIUM    = 109;  /* Mt */
  public  static final int ELEMCNT       = 126;  /* = 0x7e */
  /* The type of an element is its position in the periodic table. */

  /* --- constants: atom flags/masks --- */
  public  static final int TYPEMASK      = 0x0000007f;
  public  static final int AROMATIC      = 0x00000080;
  public  static final int CHARGEMASK    = 0x00001f00;
  public  static final int CHARGESHIFT   = 8;
  public  static final int CHAIN         = Integer.MAX_VALUE -1;
  /* The type of an atom is its position in the element map provided */
  /* by the class Elements. Additional type information comprises an */
  /* aromatic flag (bit 7, not be confused with Bond.AROMATIC) and a */
  /* charge (bit 8 to 12, coding values -15 = 0x1f to +15 = 0x0f).   */

  /* --- constants: element names --- */
  protected static final String[] names = {"*",
    "H",                                      "He",
    "Li", "Be", "B",  "C",  "N",  "O",  "F",  "Ne",
    "Na", "Mg", "Al", "Si", "P",  "S",  "Cl", "Ar",
    "K",  "Ca",
      "Sc", "Ti", "V",  "Cr", "Mn", "Fe", "Co", "Ni", "Cu", "Zn",
                "Ga", "Ge", "As", "Se", "Br", "Kr",
    "Rb", "Sr",
      "Y",  "Zr", "Nb", "Mo", "Tc", "Ru", "Rh", "Pd", "Ag", "Cd",
                "In", "Sn", "Sb", "Te", "I",  "Xe",
    "Cs", "Ba",
      "La", "Ce", "Pr", "Nd", "Pm", "Sm", "Eu", "Gd", "Tb", "Dy",
      "Ho", "Er", "Tm", "Yb",
      "Lu", "Hf", "Ta", "W",  "Re", "Os", "Ir", "Pt", "Au", "Hg",
                "Tl", "Pb", "Bi", "Po", "At", "Rn",
    "Fr", "Ra",
      "Ac", "Th", "Pa", "U",  "Np", "Pu", "Am", "Cm", "Bk", "Cf",
      "Es", "Fm", "Md", "No",
      "Lr", "Rf", "Db", "Sg", "Bh", "Hs", "Mt",

     "", "", "", "", "", "", "", "", "", "",
     "", "", "", "", "", "", "*", "*"
  };                            /* the periodic table of elements */

  /* --- constants: atoms with one letter names --- */
  protected static final int[] oneLetter = {
    HYDROGEN   /* H */, BORON      /* B */,