/// <summary> Performs a breadthFirstSearch in an AtomContainer starting with a
/// particular sphere, which usually consists of one start atom. While
/// searching the graph, the method marks each visited atom. It then puts all
/// the atoms connected to the atoms in the given sphere into a new vector
/// which forms the sphere to search for the next recursive method call. All
/// atoms that have been visited are put into a molecule container. This
/// breadthFirstSearch does thus find the connected graph for a given start
/// atom.
///
/// </summary>
/// <param name="ac"> The AtomContainer to be searched
/// </param>
/// <param name="sphere"> A sphere of atoms to start the search with
/// </param>
/// <param name="molecule">A molecule into which all the atoms and bonds are stored
/// that are found during search
/// </param>
public static void breadthFirstSearch(IAtomContainer ac, System.Collections.ArrayList sphere, IMolecule molecule, int max)
{
IAtom atom;
IAtom nextAtom;
System.Collections.ArrayList newSphere = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
for (int f = 0; f < sphere.Count; f++)
{
atom = (IAtom)sphere[f];
//System.out.println("atoms "+ atom + f);
//System.out.println("sphere size "+ sphere.size());
molecule.addAtom(atom);
// first copy LonePair's and SingleElectron's of this Atom as they need
// to be copied too
IElectronContainer[] eContainers = ac.getConnectedElectronContainers(atom);
//System.out.println("found #ec's: " + eContainers.length);
for (int i = 0; i < eContainers.Length; i++)
{
if (!(eContainers[i] is IBond))
{
// ok, no bond, thus LonePair or SingleElectron
// System.out.println("adding non bond " + eContainers[i]);
molecule.addElectronContainer(eContainers[i]);
}
}
// now look at bonds
IBond[] bonds = ac.getConnectedBonds(atom);
for (int g = 0; g < bonds.Length; g++)
{
if (!bonds[g].getFlag(CDKConstants.VISITED))
{
molecule.addBond(bonds[g]);
bonds[g].setFlag(CDKConstants.VISITED, true);
}
nextAtom = bonds[g].getConnectedAtom(atom);
if (!nextAtom.getFlag(CDKConstants.VISITED))
{
// System.out.println("wie oft???");
newSphere.Add(nextAtom);
nextAtom.setFlag(CDKConstants.VISITED, true);
}
}
if (max > -1 && molecule.AtomCount > max)
{
return;
}
}
if (newSphere.Count > 0)
{
breadthFirstSearch(ac, newSphere, molecule, max);
}
}
/// <summary> Read a Molecule from a file in MDL sd format
///
/// </summary>
/// <returns> The Molecule that was read from the MDL file.
/// </returns>
private IMolecule readMolecule(IMolecule molecule)
{
//logger.debug("Reading new molecule");
int linecount = 0;
int atoms = 0;
int bonds = 0;
int atom1 = 0;
int atom2 = 0;
int order = 0;
int stereo = 0;
int RGroupCounter = 1;
int Rnumber = 0;
System.String[] rGroup = null;
double x = 0.0;
double y = 0.0;
double z = 0.0;
double totalZ = 0.0;
//int[][] conMat = new int[0][0];
//String help;
IBond bond;
IAtom atom;
System.String line = "";
try
{
//logger.info("Reading header");
line = input.ReadLine(); linecount++;
if (line == null)
{
return(null);
}
//logger.debug("Line " + linecount + ": " + line);
if (line.StartsWith("$$$$"))
{
//logger.debug("File is empty, returning empty molecule");
return(molecule);
}
if (line.Length > 0)
{
molecule.setProperty(CDKConstants.TITLE, line);
}
line = input.ReadLine(); linecount++;
//logger.debug("Line " + linecount + ": " + line);
line = input.ReadLine(); linecount++;
//logger.debug("Line " + linecount + ": " + line);
if (line.Length > 0)
{
molecule.setProperty(CDKConstants.REMARK, line);
}
//logger.info("Reading rest of file");
line = input.ReadLine(); linecount++;
//logger.debug("Line " + linecount + ": " + line);
atoms = System.Int32.Parse(line.Substring(0, (3) - (0)).Trim());
//logger.debug("Atomcount: " + atoms);
bonds = System.Int32.Parse(line.Substring(3, (6) - (3)).Trim());
//logger.debug("Bondcount: " + bonds);
// read ATOM block
//logger.info("Reading atom block");
for (int f = 0; f < atoms; f++)
{
line = input.ReadLine(); linecount++;
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
x = System.Double.Parse(line.Substring(0, (10) - (0)).Trim());
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
y = System.Double.Parse(line.Substring(10, (20) - (10)).Trim());
//UPGRADE_TODO: The differences in the format of parameters for constructor 'java.lang.Double.Double' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'"
z = System.Double.Parse(line.Substring(20, (30) - (20)).Trim());
totalZ += System.Math.Abs(z); // *all* values should be zero, not just the sum
//logger.debug("Coordinates: " + x + "; " + y + "; " + z);
System.String element = line.Substring(31, (34) - (31)).Trim();
//logger.debug("Atom type: ", element);
if (IsotopeFactory.getInstance(molecule.Builder).isElement(element))
{
atom = IsotopeFactory.getInstance(molecule.Builder).configure(molecule.Builder.newAtom(element));
}
else
{
//logger.debug("Atom ", element, " is not an regular element. Creating a PseudoAtom.");
//check if the element is R
rGroup = element.Split(new char[] { '^', 'R' }); // ????
if (rGroup.Length > 1)
{
try
{
Rnumber = System.Int32.Parse(rGroup[(rGroup.Length - 1)]);
RGroupCounter = Rnumber;
}
catch (System.Exception ex)
{
Rnumber = RGroupCounter;
RGroupCounter++;
}
element = "R" + Rnumber;
}
atom = molecule.Builder.newPseudoAtom(element);
}
// store as 3D for now, convert to 2D (if totalZ == 0.0) later
atom.setPoint3d(new Point3d(x, y, z));
// parse further fields
System.String massDiffString = line.Substring(34, (36) - (34)).Trim();
//logger.debug("Mass difference: ", massDiffString);
if (!(atom is IPseudoAtom))
{
try
{
int massDiff = System.Int32.Parse(massDiffString);
if (massDiff != 0)
{
IIsotope major = IsotopeFactory.getInstance(molecule.Builder).getMajorIsotope(element);
atom.AtomicNumber = major.AtomicNumber + massDiff;
}
}
catch (System.Exception exception)
{
//logger.error("Could not parse mass difference field");
}
}
else
{
//logger.error("Cannot set mass difference for a non-element!");
}
System.String chargeCodeString = line.Substring(36, (39) - (36)).Trim();
//logger.debug("Atom charge code: ", chargeCodeString);
int chargeCode = System.Int32.Parse(chargeCodeString);
if (chargeCode == 0)
{
// uncharged species
}
else if (chargeCode == 1)
{
atom.setFormalCharge(+3);
}
else if (chargeCode == 2)
{
atom.setFormalCharge(+2);
}
else if (chargeCode == 3)
{
atom.setFormalCharge(+1);
}
else if (chargeCode == 4)
{
}
else if (chargeCode == 5)
{
atom.setFormalCharge(-1);
}
else if (chargeCode == 6)
{
atom.setFormalCharge(-2);
}
else if (chargeCode == 7)
{
atom.setFormalCharge(-3);
}
try
{
// read the mmm field as position 61-63
System.String reactionAtomIDString = line.Substring(60, (63) - (60)).Trim();
//logger.debug("Parsing mapping id: ", reactionAtomIDString);
try
{
int reactionAtomID = System.Int32.Parse(reactionAtomIDString);
if (reactionAtomID != 0)
{
atom.ID = reactionAtomIDString;
}
}
catch (System.Exception exception)
{
//logger.error("Mapping number ", reactionAtomIDString, " is not an integer.");
//logger.debug(exception);
}
}
catch (System.Exception exception)
{
// older mol files don't have all these fields...
//logger.warn("A few fields are missing. Older MDL MOL file?");
}
molecule.addAtom(atom);
}
// convert to 2D, if totalZ == 0
if (totalZ == 0.0 && !forceReadAs3DCoords.Set)
{
//logger.info("Total 3D Z is 0.0, interpreting it as a 2D structure");
IAtom[] atomsToUpdate = molecule.Atoms;
for (int f = 0; f < atomsToUpdate.Length; f++)
{
IAtom atomToUpdate = atomsToUpdate[f];
Point3d p3d = atomToUpdate.getPoint3d();
atomToUpdate.setPoint2d(new Point2d(p3d.x, p3d.y));
atomToUpdate.setPoint3d(null);
}
}
// read BOND block
//logger.info("Reading bond block");
for (int f = 0; f < bonds; f++)
{
line = input.ReadLine(); linecount++;
atom1 = System.Int32.Parse(line.Substring(0, (3) - (0)).Trim());
atom2 = System.Int32.Parse(line.Substring(3, (6) - (3)).Trim());
order = System.Int32.Parse(line.Substring(6, (9) - (6)).Trim());
if (line.Length > 12)
{
stereo = System.Int32.Parse(line.Substring(9, (12) - (9)).Trim());
}
else
{
//logger.warn("Missing expected stereo field at line: " + line);
}
//if (//logger.DebugEnabled)
//{
// //logger.debug("Bond: " + atom1 + " - " + atom2 + "; order " + order);
//}
if (stereo == 1)
{
// MDL up bond
stereo = CDKConstants.STEREO_BOND_UP;
}
else if (stereo == 6)
{
// MDL down bond
stereo = CDKConstants.STEREO_BOND_DOWN;
}
else if (stereo == 4)
{
//MDL bond undefined
stereo = CDKConstants.STEREO_BOND_UNDEFINED;
}
// interpret CTfile's special bond orders
IAtom a1 = molecule.getAtomAt(atom1 - 1);
IAtom a2 = molecule.getAtomAt(atom2 - 1);
if (order == 4)
{
// aromatic bond
bond = molecule.Builder.newBond(a1, a2, CDKConstants.BONDORDER_AROMATIC, stereo);
// mark both atoms and the bond as aromatic
bond.setFlag(CDKConstants.ISAROMATIC, true);
a1.setFlag(CDKConstants.ISAROMATIC, true);
a2.setFlag(CDKConstants.ISAROMATIC, true);
molecule.addBond(bond);
}
else
{
bond = molecule.Builder.newBond(a1, a2, (double)order, stereo);
molecule.addBond(bond);
}
}
// read PROPERTY block
//logger.info("Reading property block");
while (true)
{
line = input.ReadLine(); linecount++;
if (line == null)
{
throw new CDKException("The expected property block is missing!");
}
if (line.StartsWith("M END"))
{
break;
}
bool lineRead = false;
if (line.StartsWith("M CHG"))
{
// FIXME: if this is encountered for the first time, all
// atom charges should be set to zero first!
int infoCount = System.Int32.Parse(line.Substring(6, (9) - (6)).Trim());
SupportClass.Tokenizer st = new SupportClass.Tokenizer(line.Substring(9));
for (int i = 1; i <= infoCount; i++)
{
System.String token = st.NextToken();
int atomNumber = System.Int32.Parse(token.Trim());
token = st.NextToken();
int charge = System.Int32.Parse(token.Trim());
molecule.getAtomAt(atomNumber - 1).setFormalCharge(charge);
}
}
else if (line.StartsWith("M ISO"))
{
try
{
System.String countString = line.Substring(6, (9) - (6)).Trim();
int infoCount = System.Int32.Parse(countString);
SupportClass.Tokenizer st = new SupportClass.Tokenizer(line.Substring(9));
for (int i = 1; i <= infoCount; i++)
{
int atomNumber = System.Int32.Parse(st.NextToken().Trim());
int absMass = System.Int32.Parse(st.NextToken().Trim());
if (absMass != 0)
{
IAtom isotope = molecule.getAtomAt(atomNumber - 1);
isotope.MassNumber = absMass;
}
}
}
catch (System.FormatException exception)
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.getMessage' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
System.String error = "Error (" + exception.Message + ") while parsing line " + linecount + ": " + line + " in property block.";
//logger.error(error);
throw new CDKException("NumberFormatException in isotope information on line: " + line, exception);
}
}
else if (line.StartsWith("M RAD"))
{
try
{
System.String countString = line.Substring(6, (9) - (6)).Trim();
int infoCount = System.Int32.Parse(countString);
SupportClass.Tokenizer st = new SupportClass.Tokenizer(line.Substring(9));
for (int i = 1; i <= infoCount; i++)
{
int atomNumber = System.Int32.Parse(st.NextToken().Trim());
int spinMultiplicity = System.Int32.Parse(st.NextToken().Trim());
if (spinMultiplicity > 1)
{
IAtom radical = molecule.getAtomAt(atomNumber - 1);
for (int j = 2; j <= spinMultiplicity; j++)
{
// 2 means doublet -> one unpaired electron
// 3 means triplet -> two unpaired electron
molecule.addElectronContainer(molecule.Builder.newSingleElectron(radical));
}
}
}
}
catch (System.FormatException exception)
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.getMessage' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
System.String error = "Error (" + exception.Message + ") while parsing line " + linecount + ": " + line + " in property block.";
//logger.error(error);
throw new CDKException("NumberFormatException in radical information on line: " + line, exception);
}
}
else if (line.StartsWith("G "))
{
try
{
System.String atomNumberString = line.Substring(3, (6) - (3)).Trim();
int atomNumber = System.Int32.Parse(atomNumberString);
//String whatIsThisString = line.substring(6,9).trim();
System.String atomName = input.ReadLine();
// convert Atom into a PseudoAtom
IAtom prevAtom = molecule.getAtomAt(atomNumber - 1);
IPseudoAtom pseudoAtom = molecule.Builder.newPseudoAtom(atomName);
if (prevAtom.getPoint2d() != null)
{
pseudoAtom.setPoint2d(prevAtom.getPoint2d());
}
if (prevAtom.getPoint3d() != null)
{
pseudoAtom.setPoint3d(prevAtom.getPoint3d());
}
AtomContainerManipulator.replaceAtomByAtom(molecule, prevAtom, pseudoAtom);
}
catch (System.FormatException exception)
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.toString' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
System.String error = "Error (" + exception.ToString() + ") while parsing line " + linecount + ": " + line + " in property block.";
//logger.error(error);
throw new CDKException("NumberFormatException in group information on line: " + line, exception);
}
}
if (!lineRead)
{
//logger.warn("Skipping line in property block: ", line);
}
}
}
catch (CDKException exception)
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.getMessage' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
System.String error = "Error while parsing line " + linecount + ": " + line + " -> " + exception.Message;
//logger.error(error);
//logger.debug(exception);
throw exception;
}
catch (System.Exception exception)
{
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.getMessage' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
System.String error = "Error while parsing line " + linecount + ": " + line + " -> " + exception.Message;
//logger.error(error);
//logger.debug(exception);
throw new CDKException(error, exception);
}
return(molecule);
}
/// <summary> Performs a breadthFirstSearch in an AtomContainer starting with a
/// particular sphere, which usually consists of one start atom. While
/// searching the graph, the method marks each visited atom. It then puts all
/// the atoms connected to the atoms in the given sphere into a new vector
/// which forms the sphere to search for the next recursive method call. All
/// atoms that have been visited are put into a molecule container. This
/// breadthFirstSearch does thus find the connected graph for a given start
/// atom.
///
/// </summary>
/// <param name="ac"> The AtomContainer to be searched
/// </param>
/// <param name="sphere"> A sphere of atoms to start the search with
/// </param>
/// <param name="molecule">A molecule into which all the atoms and bonds are stored
/// that are found during search
/// </param>
public static void breadthFirstSearch(IAtomContainer ac, System.Collections.ArrayList sphere, IMolecule molecule, int max)
{
IAtom atom;
IAtom nextAtom;
System.Collections.ArrayList newSphere = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
for (int f = 0; f < sphere.Count; f++)
{
atom = (IAtom)sphere[f];
//System.out.println("atoms "+ atom + f);
//System.out.println("sphere size "+ sphere.size());
molecule.addAtom(atom);
// first copy LonePair's and SingleElectron's of this Atom as they need
// to be copied too
IElectronContainer[] eContainers = ac.getConnectedElectronContainers(atom);
//System.out.println("found #ec's: " + eContainers.length);
for (int i = 0; i < eContainers.Length; i++)
{
if (!(eContainers[i] is IBond))
{
// ok, no bond, thus LonePair or SingleElectron
// System.out.println("adding non bond " + eContainers[i]);
molecule.addElectronContainer(eContainers[i]);
}
}
// now look at bonds
IBond[] bonds = ac.getConnectedBonds(atom);
for (int g = 0; g < bonds.Length; g++)
{
if (!bonds[g].getFlag(CDKConstants.VISITED))
{
molecule.addBond(bonds[g]);
bonds[g].setFlag(CDKConstants.VISITED, true);
}
nextAtom = bonds[g].getConnectedAtom(atom);
if (!nextAtom.getFlag(CDKConstants.VISITED))
{
// System.out.println("wie oft???");
newSphere.Add(nextAtom);
nextAtom.setFlag(CDKConstants.VISITED, true);
}
}
if (max > -1 && molecule.AtomCount > max)
return;
}
if (newSphere.Count > 0)
{
breadthFirstSearch(ac, newSphere, molecule, max);
}
}