/** Returns true if another IMolecule can be read. */
public boolean hasNext() {
if (!nextAvailableIsKnown) {
hasNext = false;
// now try to parse the next Molecule
try {
if ((currentLine = input.readLine()) != null) {
currentFormat = (IChemFormat) MDLFormat.getInstance();
StringBuffer buffer = new StringBuffer();
while (currentLine != null && !currentLine.equals("M END")) {
// still in a molecule
buffer.append(currentLine);
buffer.append(System.getProperty("line.separator"));
currentLine = input.readLine();
// do MDL molfile version checking
if (currentLine.contains("V2000") || currentLine.contains("v2000")) {
currentFormat = (IChemFormat) MDLV2000Format.getInstance();
} else if (currentLine.contains("V3000") || currentLine.contains("v3000")) {
currentFormat = (IChemFormat) MDLV3000Format.getInstance();
}
}
buffer.append(currentLine);
buffer.append(System.getProperty("line.separator"));
logger.debug("MDL file part read: ", buffer);
ISimpleChemObjectReader reader = factory.createReader(currentFormat);
reader.setReader(new StringReader(buffer.toString()));
if (currentFormat instanceof MDLV2000Format) {
reader.addChemObjectIOListener(this);
((MDLV2000Reader) reader).customizeJob();
}
nextMolecule = (IMolecule) reader.read(builder.newInstance(IMolecule.class));
// note that a molecule may have 0 atoms, but still
// be useful (by having SD tags for example), so just
// check for null'ness rather than atom count
hasNext = nextMolecule != null;
// now read the data part
currentLine = input.readLine();
readDataBlockInto(nextMolecule);
} else {
hasNext = false;
}
} catch (Exception exception) {
logger.error("Error while reading next molecule: " + exception.getMessage());
logger.debug(exception);
hasNext = false;
}
if (!hasNext) nextMolecule = null;
nextAvailableIsKnown = true;
}
return hasNext;
}
@Test
public void checkUniqueMolecularDescriptorNames() throws Exception {
DescriptorEngine engine = new DescriptorEngine(DescriptorEngine.MOLECULAR);
List<DescriptorSpecification> specs = engine.getDescriptorSpecifications();
// we work with a simple molecule with 3D coordinates
String filename = "data/mdl/lobtest2.sdf";
InputStream ins = this.getClass().getClassLoader().getResourceAsStream(filename);
ISimpleChemObjectReader reader = new MDLV2000Reader(ins);
ChemFile content = (ChemFile) reader.read(new ChemFile());
List cList = ChemFileManipulator.getAllAtomContainers(content);
IAtomContainer ac = (IAtomContainer) cList.get(0);
AtomContainerManipulator.percieveAtomTypesAndConfigureAtoms(ac);
engine.process(ac);
int ncalc = 0;
List<String> descNames = new ArrayList<String>();
for (DescriptorSpecification spec : specs) {
DescriptorValue value = (DescriptorValue) ac.getProperty(spec);
if (value == null) continue;
ncalc++;
String[] names = value.getNames();
descNames.addAll(Arrays.asList(names));
}
List<String> dups = new ArrayList<String>();
Set<String> uniqueNames = new HashSet<String>();
for (String name : descNames) {
if (!uniqueNames.add(name)) dups.add(name);
}
Assert.assertEquals(specs.size(), ncalc);
Assert.assertEquals(descNames.size(), uniqueNames.size());
if (dups.size() != 0) {
System.out.println("Following names were duplicated");
for (String dup : dups) {
System.out.println("dup = " + dup);
}
}
}
/**
* Returns an IChemModel, using the reader provided (picked).
*
* @param cor
* @param panel
* @return
* @throws CDKException
*/
public static IChemModel getChemModelFromReader(
final ISimpleChemObjectReader cor,
final AbstractJChemPaintPanel panel) throws CDKException {
panel.get2DHub().setRGroupHandler(null);
String error = null;
ChemModel chemModel = null;
IChemFile chemFile = null;
if (cor.accepts(IChemFile.class) && chemModel == null) {
// try to read a ChemFile
try {
chemFile = (IChemFile) cor.read((IChemObject) new ChemFile());
if (chemFile == null) {
error = "The object chemFile was empty unexpectedly!";
}
} catch (final Exception exception) {
error = "Error while reading file: " + exception.getMessage();
exception.printStackTrace();
}
}
if (error != null) {
throw new CDKException(error);
}
if (chemModel == null && chemFile != null) {
chemModel = (ChemModel) chemFile.getChemSequence(0).getChemModel(0);
}
if (cor.accepts(ChemModel.class) && chemModel == null) {
// try to read a ChemModel
try {
chemModel = (ChemModel) cor.read((IChemObject) new ChemModel());
if (chemModel == null) {
error = "The object chemModel was empty unexpectedly!";
}
} catch (final Exception exception) {
error = "Error while reading file: " + exception.getMessage();
exception.printStackTrace();
}
}
// Smiles reading
if (cor.accepts(AtomContainerSet.class) && chemModel == null) {
// try to read a AtomContainer set
try {
final IAtomContainerSet som = cor.read(new AtomContainerSet());
chemModel = new ChemModel();
chemModel.setMoleculeSet(som);
if (chemModel == null) {
error = "The object chemModel was empty unexpectedly!";
}
} catch (final Exception exception) {
error = "Error while reading file: " + exception.getMessage();
exception.printStackTrace();
}
}
// MDLV3000 reading
if (cor.accepts(AtomContainer.class) && chemModel == null) {
// try to read a AtomContainer
final IAtomContainer mol = cor.read(new AtomContainer());
if (mol != null) {
try {
final IAtomContainerSet newSet = new AtomContainerSet();
newSet.addAtomContainer(mol);
chemModel = new ChemModel();
chemModel.setMoleculeSet(newSet);
if (chemModel == null) {
error = "The object chemModel was empty unexpectedly!";
}
} catch (final Exception exception) {
error = "Error while reading file: "
+ exception.getMessage();
exception.printStackTrace();
}
}
}
// RGroupQuery reading
if (cor.accepts(RGroupQuery.class) && chemModel == null) {
final IRGroupQuery rgroupQuery = cor.read(new RGroupQuery());
if (rgroupQuery != null) {
try {
chemModel = new ChemModel();
final RGroupHandler rgHandler = new RGroupHandler(
rgroupQuery);
panel.get2DHub().setRGroupHandler(rgHandler);
chemModel.setMoleculeSet(rgHandler
.getMoleculeSet(chemModel));
rgHandler.layoutRgroup();
} catch (final Exception exception) {
error = "Error while reading file: "
+ exception.getMessage();
exception.printStackTrace();
}
}
}
if (error != null) {
throw new CDKException(error);
}
if (chemModel == null && chemFile != null) {
chemModel = (ChemModel) chemFile.getChemSequence(0).getChemModel(0);
}
// SmilesParser sets valencies, switch off by default.
if (cor instanceof SMILESReader) {
final IAtomContainer allinone = JChemPaintPanel
.getAllAtomContainersInOne(chemModel);
for (int k = 0; k < allinone.getAtomCount(); k++) {
allinone.getAtom(k).setValency(null);
}
}
return chemModel;
}
/**
* Loads one or more files into IAtomContainer objects.
*
* <p>This method does not need knowledge of the format since it is autodetected. Note that if
* aromaticity detection or atom typing is specified and fails for a specific molecule, that
* molecule will be set to <i>null</i>
*
* @param filenames An array of String's containing the filenames of the structures we want to
* load
* @param doAromaticity If true, then aromaticity perception is performed
* @param doTyping If true, atom typing and configuration is performed. This will use the internal
* CDK atom typing scheme
* @return An array of AtoContainer's
* @throws CDKException if there is an error when reading a file
*/
public static IAtomContainer[] loadMolecules(
String[] filenames, boolean doAromaticity, boolean doTyping, boolean doIsotopes)
throws CDKException, IOException {
Vector<IAtomContainer> v = new Vector<IAtomContainer>();
IChemObjectBuilder builder = DefaultChemObjectBuilder.getInstance();
try {
int i;
int j;
for (i = 0; i < filenames.length; i++) {
File input = new File(filenames[i]);
ReaderFactory readerFactory = new ReaderFactory();
ISimpleChemObjectReader reader = readerFactory.createReader(new FileReader(input));
if (reader == null) { // see if it's a SMI file
if (filenames[i].endsWith(".smi")) {
reader = new SMILESReader(new FileReader(input));
}
}
IChemFile content = (IChemFile) reader.read(builder.newInstance(IChemFile.class));
if (content == null) continue;
List<IAtomContainer> c = ChemFileManipulator.getAllAtomContainers(content);
// we should do this loop in case we have files
// that contain multiple molecules
v.addAll(c);
}
} catch (Exception e) {
e.printStackTrace();
throw new CDKException(e.toString());
}
// convert the vector to a simple array
IAtomContainer[] retValues = new IAtomContainer[v.size()];
for (int i = 0; i < v.size(); i++) {
retValues[i] = v.get(i);
}
// before returning, lets make see if we
// need to perceive aromaticity and atom typing
if (doAromaticity) {
for (int i = 0; i < retValues.length; i++) {
try {
CDKHueckelAromaticityDetector.detectAromaticity(retValues[i]);
} catch (CDKException e) {
retValues[i] = null;
}
}
}
if (doTyping) {
for (int i = 0; i < retValues.length; i++) {
try {
AtomContainerManipulator.percieveAtomTypesAndConfigureAtoms(retValues[i]);
} catch (CDKException e) {
retValues[i] = null;
}
}
}
if (doIsotopes) {
IsotopeFactory ifac = IsotopeFactory.getInstance(DefaultChemObjectBuilder.getInstance());
for (IAtomContainer retValue : retValues) {
ifac.configureAtoms(retValue);
}
}
return retValues;
}