use of ambit2.dbcli.processor.StdzBatchProcessor in project ambit-mirror by ideaconsult.
the class AmbitPipeline method parseCommandStandardize.
public void parseCommandStandardize(String subcommand, long now) throws Exception {
int page = parsePageParam();
int pagesize = parsePageSizeParam();
Object tmpTag = parseSdfTitleParam();
String smiles_header = parseInputTag_Param("smiles", IteratingDelimitedFileReader.defaultSMILESHeader);
String inchi_header = parseInputTag_Param("inchi", "InChI");
String inchikey_header = parseInputTag_Param("inchikey", "InChIKey");
final String sdf_title = tmpTag == null ? null : tmpTag.toString().toLowerCase();
final StructureStandardizer standardprocessor = new StructureStandardizer(logger_cli);
standardprocessor.setGenerate2D(parseBooleanParam(":generate2D", false));
standardprocessor.setGenerateTautomers(parseBooleanParam(":tautomers", false));
SMIRKSProcessor tmp = null;
try {
Object o = options.getParam(":smirks");
if (o != null) {
File smirksConfig = new File(o.toString());
if (smirksConfig.exists()) {
tmp = new SMIRKSProcessor(smirksConfig, logger_cli);
tmp.setEnabled(true);
} else
logger_cli.log(Level.WARNING, "SMIRKS transformation file not found");
}
} catch (Exception x) {
logger_cli.log(Level.SEVERE, x.getMessage());
tmp = null;
}
final SMIRKSProcessor smirksProcessor = tmp;
standardprocessor.setSplitFragments(parseBooleanParam(":splitfragments", false));
standardprocessor.setImplicitHydrogens(parseBooleanParam(":implicith", false));
standardprocessor.setNeutralise(parseBooleanParam(":neutralise", false));
final String[] tags_to_keep = parsetags_to_keep();
standardprocessor.setRankTag(parseStringParam(":tag_rank", "RANK"));
standardprocessor.setInchiTag(parseStringParam(":tag_inchi", "InChI"));
standardprocessor.setInchiKeyTag(parseStringParam(":tag_inchikey", "InChIKey"));
standardprocessor.setSMILESTag(parseStringParam(":tag_smiles", "SMILES"));
standardprocessor.setGenerateInChI(parseBooleanParam(":inchi", true));
standardprocessor.setGenerateSMILES(parseBooleanParam(":smiles", true));
standardprocessor.setGenerateSMILES_Canonical(parseBooleanParam(":smilescanonical", false));
standardprocessor.setGenerateSMILES_Aromatic(parseBooleanParam(":smilesaromatic", false));
standardprocessor.setGenerateStereofrom2D(parseBooleanParam(":generatestereofrom2d", false));
standardprocessor.setClearIsotopes(parseBooleanParam(":setClearIsotopes", false));
final boolean debugatomtypes = parseBooleanParam(":debugatomtypes", false);
final int startRecord = pagesize > 0 ? (page * pagesize + 1) : 1;
final int maxRecord = pagesize > 0 ? ((page + 1) * pagesize + 1) : pagesize;
final File file = getInputFile();
FileInputState in = new FileInputState(file);
in.setOptionalInChIHeader(inchi_header);
in.setOptionalInChIKeyHeader(inchikey_header);
in.setOptionalSMILESHeader(smiles_header);
if (options.output == null)
throw new FileNotFoundException("Output file not specified. Please use -o {file}");
final File outfile = new File(options.output);
logger_cli.log(Level.INFO, "MSG_INFO_READINGWRITING", new Object[] { file.getAbsoluteFile(), outfile.getAbsolutePath() });
FileOutputState out = new FileOutputState(outfile);
final IChemObjectWriter writer = out.getWriter();
if (writer instanceof FilesWithHeaderWriter)
((FilesWithHeaderWriter) writer).setAddSMILEScolumn(false);
final BatchDBProcessor<IStructureRecord> batch = new BatchDBProcessor<IStructureRecord>() {
@Override
public void onItemRead(IStructureRecord input, IBatchStatistics stats) {
super.onItemRead(input, stats);
if ((maxRecord > 0) && stats.getRecords(RECORDS_STATS.RECORDS_READ) >= (maxRecord))
cancel();
}
@Override
public boolean skip(IStructureRecord input, IBatchStatistics stats) {
return (stats.getRecords(RECORDS_STATS.RECORDS_READ) < startRecord) || ((maxRecord > 0) && (stats.getRecords(RECORDS_STATS.RECORDS_READ) >= maxRecord));
}
@Override
public void onItemSkipped(IStructureRecord input, IBatchStatistics stats) {
super.onItemSkipped(input, stats);
if (stats.isTimeToPrint(getSilentInterval() * 2))
propertyChangeSupport.firePropertyChange(PROPERTY_BATCHSTATS, null, stats);
}
@Override
public void onItemProcessing(IStructureRecord input, Object output, IBatchStatistics stats) {
}
@Override
public void onError(IStructureRecord input, Object output, IBatchStatistics stats, Exception x) {
super.onError(input, output, stats, x);
logger_cli.log(Level.SEVERE, x.getMessage());
}
@Override
public long getSilentInterval() {
return 30000L;
}
@Override
public void close() throws Exception {
try {
writer.close();
} catch (Exception x) {
} finally {
}
super.close();
}
};
batch.setProcessorChain(new ProcessorsChain<IStructureRecord, IBatchStatistics, IProcessor>());
batch.getProcessorChain().add(new StdzBatchProcessor(standardprocessor, smirksProcessor, tags_to_keep, logger_cli, writer, sdf_title, debugatomtypes));
batch.addPropertyChangeListener(new PropertyChangeListener() {
@Override
public void propertyChange(PropertyChangeEvent evt) {
if (AbstractBatchProcessor.PROPERTY_BATCHSTATS.equals(evt.getPropertyName()))
logger_cli.log(Level.INFO, evt.getNewValue().toString());
}
});
/*
* standardprocessor.setCallback(new
* DefaultAmbitProcessor<IAtomContainer, IAtomContainer>() {
*
* @Override public IAtomContainer process(IAtomContainer target) throws
* Exception { try { //writer.write(target); } catch (Exception x) {
* logger.log(Level.SEVERE, x.getMessage()); } return target; } });
*/
IBatchStatistics stats = null;
try {
stats = batch.process(in);
} catch (Exception x) {
StringWriter w = new StringWriter();
x.printStackTrace(new PrintWriter(w));
logger_cli.log(Level.WARNING, "MSG_ERR", new Object[] { x.getMessage() });
logger_cli.log(Level.FINE, "MSG_ERR_DEBUG", new Object[] { x.getMessage(), w.toString() });
} finally {
try {
if (batch != null)
batch.close();
} catch (Exception x) {
logger_cli.log(Level.WARNING, "MSG_ERR", new Object[] { x.getMessage() });
}
if (stats != null)
logger_cli.log(Level.INFO, "MSG_INFO", new Object[] { stats.toString() });
}
}
Aggregations