// private procedures
/// <summary> Private method that actually parses the input to read a ChemFile
/// object.
///
/// </summary>
/// <returns> A ChemFile containing the data parsed from input.
/// </returns>
private IChemFile readChemFile(IChemFile file)
{
IChemSequence chemSequence = file.Builder.newChemSequence();
int number_of_atoms = 0;
SupportClass.Tokenizer tokenizer;
try
{
System.String line = input.ReadLine();
while (input.Peek() != -1 && line != null)
{
// parse frame by frame
tokenizer = new SupportClass.Tokenizer(line, "\t ,;");
System.String token = tokenizer.NextToken();
number_of_atoms = System.Int32.Parse(token);
System.String info = input.ReadLine();
IChemModel chemModel = file.Builder.newChemModel();
ISetOfMolecules setOfMolecules = file.Builder.newSetOfMolecules();
IMolecule m = file.Builder.newMolecule();
m.setProperty(CDKConstants.TITLE, info);
for (int i = 0; i < number_of_atoms; i++)
{
line = input.ReadLine();
if (line == null)
{
break;
}
if (line.StartsWith("#") && line.Length > 1)
{
System.Object comment = m.getProperty(CDKConstants.COMMENT);
if (comment == null)
{
comment = "";
}
//UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Object.toString' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'"
comment = comment.ToString() + line.Substring(1).Trim();
m.setProperty(CDKConstants.COMMENT, comment);
//logger.debug("Found and set comment: ", comment);
}
else
{
double x = 0.0f, y = 0.0f, z = 0.0f;
double charge = 0.0f;
tokenizer = new SupportClass.Tokenizer(line, "\t ,;");
int fields = tokenizer.Count;
if (fields < 4)
{
// this is an error but cannot throw exception
}
else
{
System.String atomtype = tokenizer.NextToken();
//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(tokenizer.NextToken()));
//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(tokenizer.NextToken()));
//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(tokenizer.NextToken()));
if (fields == 8)
{
//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'"
charge = (System.Double.Parse(tokenizer.NextToken()));
}
IAtom atom = file.Builder.newAtom(atomtype, new Point3d(x, y, z));
atom.setCharge(charge);
m.addAtom(atom);
}
}
}
setOfMolecules.addMolecule(m);
chemModel.SetOfMolecules = setOfMolecules;
chemSequence.addChemModel(chemModel);
line = input.ReadLine();
}
file.addChemSequence(chemSequence);
}
catch (System.IO.IOException e)
{
// should make some noise now
file = null;
//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'"
//logger.error("Error while reading file: ", e.Message);
//logger.debug(e);
}
return(file);
}
/// <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> Private method that actually parses the input to read a ChemFile
/// object.
///
/// </summary>
/// <returns> A ChemFile containing the data parsed from input.
/// </returns>
private IChemFile readChemFile(IChemFile file)
{
IChemSequence chemSequence = file.Builder.newChemSequence();
int number_of_atoms = 0;
SupportClass.Tokenizer tokenizer;
try
{
System.String line = input.ReadLine();
while (line.StartsWith("#"))
{
line = input.ReadLine();
}
/*while (input.ready() && line != null)
* {*/
// System.out.println("lauf");
// parse frame by frame
tokenizer = new SupportClass.Tokenizer(line, "\t ,;");
System.String token = tokenizer.NextToken();
number_of_atoms = System.Int32.Parse(token);
System.String info = input.ReadLine();
IChemModel chemModel = file.Builder.newChemModel();
ISetOfMolecules setOfMolecules = file.Builder.newSetOfMolecules();
IMolecule m = file.Builder.newMolecule();
m.setProperty(CDKConstants.TITLE, info);
System.String[] types = new System.String[number_of_atoms];
double[] d = new double[number_of_atoms]; int[] d_atom = new int[number_of_atoms]; // Distances
double[] a = new double[number_of_atoms]; int[] a_atom = new int[number_of_atoms]; // Angles
double[] da = new double[number_of_atoms]; int[] da_atom = new int[number_of_atoms]; // Diederangles
//Point3d[] pos = new Point3d[number_of_atoms]; // calculated positions
int i = 0;
while (i < number_of_atoms)
{
line = input.ReadLine();
// System.out.println("line:\""+line+"\"");
if (line == null)
{
break;
}
if (line.StartsWith("#"))
{
// skip comment in file
}
else
{
d[i] = 0d; d_atom[i] = -1;
a[i] = 0d; a_atom[i] = -1;
da[i] = 0d; da_atom[i] = -1;
tokenizer = new SupportClass.Tokenizer(line, "\t ,;");
int fields = tokenizer.Count;
if (fields < System.Math.Min(i * 2 + 1, 7))
{
// this is an error but cannot throw exception
}
else if (i == 0)
{
types[i] = tokenizer.NextToken();
i++;
}
else if (i == 1)
{
types[i] = tokenizer.NextToken();
d_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//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'"
d[i] = (System.Double.Parse(tokenizer.NextToken()));
i++;
}
else if (i == 2)
{
types[i] = tokenizer.NextToken();
d_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//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'"
d[i] = (System.Double.Parse(tokenizer.NextToken()));
a_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//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'"
a[i] = (System.Double.Parse(tokenizer.NextToken()));
i++;
}
else
{
types[i] = tokenizer.NextToken();
d_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//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'"
d[i] = (System.Double.Parse(tokenizer.NextToken()));
a_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//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'"
a[i] = (System.Double.Parse(tokenizer.NextToken()));
da_atom[i] = (System.Int32.Parse(tokenizer.NextToken())) - 1;
//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'"
da[i] = (System.Double.Parse(tokenizer.NextToken()));
i++;
}
}
}
// calculate cartesian coordinates
Point3d[] cartCoords = ZMatrixTools.zmatrixToCartesian(d, d_atom, a, a_atom, da, da_atom);
for (i = 0; i < number_of_atoms; i++)
{
m.addAtom(file.Builder.newAtom(types[i], cartCoords[i]));
}
// System.out.println("molecule:\n"+m);
setOfMolecules.addMolecule(m);
chemModel.SetOfMolecules = setOfMolecules;
chemSequence.addChemModel(chemModel);
line = input.ReadLine();
file.addChemSequence(chemSequence);
}
catch (System.IO.IOException e)
{
// should make some noise now
file = null;
}
return(file);
}
/// <summary> Read a ChemFile from a file in MDL SDF format.
///
/// </summary>
/// <returns> The ChemFile that was read from the MDL file.
/// </returns>
private IChemFile readChemFile(IChemFile chemFile)
{
IChemSequence chemSequence = chemFile.Builder.newChemSequence();
IChemModel chemModel = chemFile.Builder.newChemModel();
ISetOfMolecules setOfMolecules = chemFile.Builder.newSetOfMolecules();
IMolecule m = readMolecule(chemFile.Builder.newMolecule());
if (m != null)
{
setOfMolecules.addMolecule(m);
}
chemModel.SetOfMolecules = setOfMolecules;
chemSequence.addChemModel(chemModel);
setOfMolecules = chemFile.Builder.newSetOfMolecules();
chemModel = chemFile.Builder.newChemModel();
System.String str;
try
{
System.String line;
while ((line = input.ReadLine()) != null)
{
//logger.debug("line: ", line);
// apparently, this is a SDF file, continue with
// reading mol files
str = new System.Text.StringBuilder(line).ToString();
if (str.Equals("$$$$"))
{
m = readMolecule(chemFile.Builder.newMolecule());
if (m != null)
{
setOfMolecules.addMolecule(m);
chemModel.SetOfMolecules = setOfMolecules;
chemSequence.addChemModel(chemModel);
setOfMolecules = chemFile.Builder.newSetOfMolecules();
chemModel = chemFile.Builder.newChemModel();
}
}
else
{
// here the stuff between 'M END' and '$$$$'
if (m != null)
{
// ok, the first lines should start with '>'
System.String fieldName = null;
if (str.StartsWith("> "))
{
// ok, should extract the field name
str.Substring(2); // String content =
int index = str.IndexOf("<");
if (index != -1)
{
int index2 = str.Substring(index).IndexOf(">");
if (index2 != -1)
{
fieldName = str.Substring(index + 1, (index + index2) - (index + 1));
}
}
// end skip all other lines
while ((line = input.ReadLine()) != null && line.StartsWith(">"))
{
//logger.debug("data header line: ", line);
}
}
if (line == null)
{
throw new CDKException("Expecting data line here, but found null!");
}
System.String data = line;
while ((line = input.ReadLine()) != null && line.Trim().Length > 0)
{
if (line.Equals("$$$$"))
{
//logger.error("Expecting data line here, but found end of molecule: ", line);
break;
}
//logger.debug("data line: ", line);
data += line;
}
if (fieldName != null)
{
//logger.info("fieldName, data: ", fieldName, ", ", data);
m.setProperty(fieldName, data);
}
}
}
}
}
catch (CDKException cdkexc)
{
throw cdkexc;
}
catch (System.Exception exception)
{
System.String error = "Error while parsing SDF";
//logger.error(error);
//logger.debug(exception);
throw new CDKException(error, exception);
}
try
{
input.Close();
}
catch (System.Exception exc)
{
//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 closing file: " + exc.Message;
//logger.error(error);
throw new CDKException(error, exc);
}
chemFile.addChemSequence(chemSequence);
return(chemFile);
}
/// <summary> Private method that actually parses the input to read a ChemFile
/// object. In its current state it is able to read all the molecules
/// (if more than one is present) in the specified HIN file. These are
/// placed in a SetOfMolecules object which in turn is placed in a ChemModel
/// which in turn is placed in a ChemSequence object and which is finally
/// placed in a ChemFile object and returned to the user.
///
/// </summary>
/// <returns> A ChemFile containing the data parsed from input.
/// </returns>
private IChemFile readChemFile(IChemFile file)
{
IChemSequence chemSequence = file.Builder.newChemSequence();
IChemModel chemModel = file.Builder.newChemModel();
ISetOfMolecules setOfMolecules = file.Builder.newSetOfMolecules();
System.String info;
SupportClass.Tokenizer tokenizer;
try
{
System.String line;
// read in header info
while (true)
{
line = input.ReadLine();
if (line.IndexOf("mol ") == 0)
{
info = getMolName(line);
break;
}
}
// start the actual molecule data - may be multiple molecule
line = input.ReadLine();
while (true)
{
if (line == null)
{
break; // end of file
}
if (line.IndexOf(';') == 0)
{
continue; // comment line
}
if (line.IndexOf("mol ") == 0)
{
info = getMolName(line);
line = input.ReadLine();
}
IMolecule m = file.Builder.newMolecule();
m.setProperty(CDKConstants.TITLE, info);
// Each elemnt of cons is an ArrayList of length 3 which stores
// the start and end indices and bond order of each bond
// found in the HIN file. Before adding bonds we need to reduce
// the number of bonds so as not to count the same bond twice
System.Collections.ArrayList cons = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
// read data for current molecule
int atomSerial = 0;
while (true)
{
if (line.IndexOf("endmol ") >= 0)
{
break;
}
if (line.IndexOf(';') == 0)
{
continue; // comment line
}
tokenizer = new SupportClass.Tokenizer(line, " ");
int ntoken = tokenizer.Count;
System.String[] toks = new System.String[ntoken];
for (int i = 0; i < ntoken; i++)
{
toks[i] = tokenizer.NextToken();
}
System.String sym = new System.Text.StringBuilder(toks[3]).ToString();
double charge = System.Double.Parse(toks[6]);
double x = System.Double.Parse(toks[7]);
double y = System.Double.Parse(toks[8]);
double z = System.Double.Parse(toks[9]);
int nbond = System.Int32.Parse(toks[10]);
IAtom atom = file.Builder.newAtom(sym, new Point3d(x, y, z));
atom.setCharge(charge);
for (int j = 11; j < (11 + nbond * 2); j += 2)
{
double bo = 1;
int s = System.Int32.Parse(toks[j]) - 1; // since atoms start from 1 in the file
char bt = toks[j + 1][0];
switch (bt)
{
case 's':
bo = 1;
break;
case 'd':
bo = 2;
break;
case 't':
bo = 3;
break;
case 'a':
bo = 1.5;
break;
}
System.Collections.ArrayList ar = new System.Collections.ArrayList(3);
ar.Add((System.Int32)atomSerial);
ar.Add((System.Int32)s);
ar.Add((double)bo);
cons.Add(ar);
}
m.addAtom(atom);
atomSerial++;
line = input.ReadLine();
}
// before storing the molecule lets include the connections
// First we reduce the number of bonds stored, since we have
// stored both, say, C1-H1 and H1-C1.
System.Collections.ArrayList blist = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
for (int i = 0; i < cons.Count; i++)
{
System.Collections.ArrayList ar = (System.Collections.ArrayList)cons[i];
// make a reversed list
System.Collections.ArrayList arev = new System.Collections.ArrayList(3);
arev.Add(ar[1]);
arev.Add(ar[0]);
arev.Add(ar[2]);
// Now see if ar or arev are already in blist
if (blist.Contains(ar) || blist.Contains(arev))
{
continue;
}
else
{
blist.Add(ar);
}
}
// now just store all the bonds we have
for (int i = 0; i < blist.Count; i++)
{
System.Collections.ArrayList ar = (System.Collections.ArrayList)blist[i];
int s = ((System.Int32)ar[0]);
int e = ((System.Int32)ar[1]);
double bo = ((System.Double)ar[2]);
m.addBond(s, e, bo);
}
setOfMolecules.addMolecule(m);
line = input.ReadLine(); // read in the 'mol N'
}
// got all the molecule in the HIN file (hopefully!)
chemModel.SetOfMolecules = setOfMolecules;
chemSequence.addChemModel(chemModel);
file.addChemSequence(chemSequence);
}
catch (System.IO.IOException e)
{
// should make some noise now
file = null;
}
return(file);
}