@Override
public byte[] encode() {
byte[] bytes = new byte[encodedSize()];
bytes[0] = (byte) 0x80;
BitWriter bitWriter = new BitWriter(bytes, 0, bytes.length, 5, true);
int lastSetBit = -1;
for (int setPos = bitSet.nextSetBit(0); setPos >= 0; setPos = bitSet.nextSetBit(setPos + 1)) {
// skip the distance between setPos and lastSetBit
bitWriter.skip(setPos - lastSetBit - 1);
/*
* Because this field is present, we need to use 2 bits to indicate the
* type information necessary to parse. The format for the type bit is
*
* Untyped: 00
* Double: 01
* Float: 10
* Scalar: 11
*/
if (scalarFields != null && scalarFields.get(setPos)) {
bitWriter.set(3);
} else if (floatFields != null && floatFields.get(setPos)) {
bitWriter.set(2);
bitWriter.skipNext();
} else if (doubleFields != null && doubleFields.get(setPos)) {
bitWriter.setNext();
bitWriter.skipNext();
bitWriter.setNext();
} else {
bitWriter.setNext();
bitWriter.skip(2);
}
lastSetBit = setPos;
}
return bytes;
}
@Override
public int cardinality(int position) {
int count = 0;
for (int i = bitSet.nextSetBit(0); i >= 0 && i < position; i = bitSet.nextSetBit(i + 1)) {
count++;
}
return count;
}
@Override
public int nextSetBit(int currentPosition) {
return bitSet.nextSetBit(currentPosition);
}
/**
* Performs the actual clustering with an assumption that all documents are written in one <code>
* language</code>.
*/
private void cluster(LanguageCode language) {
// Preprocessing of documents
final PreprocessingContext context =
preprocessingPipeline.preprocess(documents, query, language);
// Further processing only if there are words to process
clusters = Lists.newArrayList();
if (context.hasLabels()) {
// Term-document matrix building and reduction
final VectorSpaceModelContext vsmContext = new VectorSpaceModelContext(context);
final ReducedVectorSpaceModelContext reducedVsmContext =
new ReducedVectorSpaceModelContext(vsmContext);
LingoProcessingContext lingoContext = new LingoProcessingContext(reducedVsmContext);
matrixBuilder.buildTermDocumentMatrix(vsmContext);
matrixBuilder.buildTermPhraseMatrix(vsmContext);
matrixReducer.reduce(
reducedVsmContext, computeClusterCount(desiredClusterCountBase, documents.size()));
// Cluster label building
clusterBuilder.buildLabels(lingoContext, matrixBuilder.termWeighting);
// Document assignment
clusterBuilder.assignDocuments(lingoContext);
// Cluster merging
clusterBuilder.merge(lingoContext);
// Format final clusters
final int[] clusterLabelIndex = lingoContext.clusterLabelFeatureIndex;
final BitSet[] clusterDocuments = lingoContext.clusterDocuments;
final double[] clusterLabelScore = lingoContext.clusterLabelScore;
for (int i = 0; i < clusterLabelIndex.length; i++) {
final Cluster cluster = new Cluster();
final int labelFeature = clusterLabelIndex[i];
if (labelFeature < 0) {
// Cluster removed during merging
continue;
}
// Add label and score
cluster.addPhrases(labelFormatter.format(context, labelFeature));
cluster.setAttribute(Cluster.SCORE, clusterLabelScore[i]);
// Add documents
final BitSet bs = clusterDocuments[i];
for (int bit = bs.nextSetBit(0); bit >= 0; bit = bs.nextSetBit(bit + 1)) {
cluster.addDocuments(documents.get(bit));
}
// Add cluster
clusters.add(cluster);
}
Collections.sort(clusters, Cluster.byReversedWeightedScoreAndSizeComparator(scoreWeight));
}
Cluster.appendOtherTopics(documents, clusters);
}
