@Override
public void initialize(UimaContext context) throws ResourceInitializationException {
super.initialize(context);
try {
this.converter = new Web1TConverter(outputPath, minNgramLength, maxNgramLength);
} catch (IOException e) {
throw new ResourceInitializationException(e);
}
converter.setWriteIndexes(createIndexes);
converter.setSplitThreshold(splitThreshold);
converter.setMinFrequency(minFreq);
converter.setToLowercase(lowercase);
converter.setOutputEncoding(outputEncoding);
}
@Override
public void process(JCas jcas) throws AnalysisEngineProcessException {
try {
converter.add(jcas, inputPaths, jcas.getCas().getTypeSystem().getType(contextType));
} catch (IOException e) {
throw new AnalysisEngineProcessException(e);
}
}
/**
* The input files for each ngram level is read, splitted according to the frequency of the words
* starting letter in the files and the split files are individually sorted and consolidated.
*/
@Override
public void collectionProcessComplete() throws AnalysisEngineProcessException {
super.collectionProcessComplete();
try {
converter.createIndex();
} catch (IOException e) {
throw new AnalysisEngineProcessException(e);
}
}
