Java Code Examples for org.apache.lucene.index.TermStates#build()

Map<Term,TermStatistics> getNodeTermStats(Set<Term> terms, int nodeID, long version) throws IOException {
  final NodeState node = nodes[nodeID];
  final Map<Term,TermStatistics> stats = new HashMap<>();
  final IndexSearcher s = node.searchers.acquire(version);
  if (s == null) {
    throw new SearcherExpiredException("node=" + nodeID + " version=" + version);
  }
  try {
    for(Term term : terms) {
      final TermStates ts = TermStates.build(s.getIndexReader().getContext(), term, true);
      if (ts.docFreq() > 0) {
        stats.put(term, s.termStatistics(term, ts.docFreq(), ts.totalTermFreq()));
      }
    }
  } finally {
    node.searchers.release(s);
  }
  return stats;
}
 

@Override
public Query rewrite(IndexReader reader) throws IOException {
    Query rewritten = super.rewrite(reader);
    if (rewritten != this) {
        return rewritten;
    }
    IndexReaderContext context = reader.getContext();
    TermStates[] ctx = new TermStates[terms.length];
    int[] docFreqs = new int[ctx.length];
    for (int i = 0; i < terms.length; i++) {
        ctx[i] = TermStates.build(context, terms[i], true);
        docFreqs[i] = ctx[i].docFreq();
    }

    final int maxDoc = reader.maxDoc();
    blend(ctx, maxDoc, reader);
    return topLevelQuery(terms, ctx, docFreqs, maxDoc);
}
 

@Override
public Weight createWeight(IndexSearcher searcher, ScoreMode scoreMode, float boost) throws IOException {
  final IndexReaderContext context = searcher.getTopReaderContext();
  final TermStates termState;
  if (perReaderTermState == null
      || perReaderTermState.wasBuiltFor(context) == false) {
    termState = TermStates.build(context, term, scoreMode.needsScores());
  } else {
    // PRTS was pre-build for this IS
    termState = this.perReaderTermState;
  }

  return new TermWeight(searcher, scoreMode, boost, termState);
}
 

@Override
public SpanWeight createWeight(IndexSearcher searcher, ScoreMode scoreMode, float boost) throws IOException {
  final TermStates context;
  final IndexReaderContext topContext = searcher.getTopReaderContext();
  if (termStates == null || termStates.wasBuiltFor(topContext) == false) {
    context = TermStates.build(topContext, term, scoreMode.needsScores());
  }
  else {
    context = termStates;
  }
  return new SpanTermWeight(context, searcher, scoreMode.needsScores() ? Collections.singletonMap(term, context) : null, boost);
}
 

@Override
public final Query rewrite(IndexReader reader) throws IOException {
  final TermStates[] contexts = ArrayUtil.copyOfSubArray(this.contexts, 0, this.contexts.length);
  for (int i = 0; i < contexts.length; ++i) {
    if (contexts[i] == null || contexts[i].wasBuiltFor(reader.getContext()) == false) {
      contexts[i] = TermStates.build(reader.getContext(), terms[i], true);
    }
  }

  // Compute aggregated doc freq and total term freq
  // df will be the max of all doc freqs
  // ttf will be the sum of all total term freqs
  int df = 0;
  long ttf = 0;
  for (TermStates ctx : contexts) {
    df = Math.max(df, ctx.docFreq());
    ttf += ctx.totalTermFreq();
  }

  for (int i = 0; i < contexts.length; ++i) {
    contexts[i] = adjustFrequencies(reader.getContext(), contexts[i], df, ttf);
  }

  Query[] termQueries = new Query[terms.length];
  for (int i = 0; i < terms.length; ++i) {
    termQueries[i] = new TermQuery(terms[i], contexts[i]);
    if (boosts[i] != 1f) {
      termQueries[i] = new BoostQuery(termQueries[i], boosts[i]);
    }
  }
  return rewriteMethod.rewrite(termQueries);
}
 

/**
 * Compute a feature value that may be used as the {@code pivot} parameter of
 * the {@link #newSaturationQuery(String, String, float, float)} and
 * {@link #newSigmoidQuery(String, String, float, float, float)} factory
 * methods. The implementation takes the average of the int bits of the float
 * representation in practice before converting it back to a float. Given that
 * floats store the exponent in the higher bits, it means that the result will
 * be an approximation of the geometric mean of all feature values.
 * @param reader       the {@link IndexReader} to search against
 * @param featureField the field that stores features
 * @param featureName  the name of the feature
 */
static float computePivotFeatureValue(IndexReader reader, String featureField, String featureName) throws IOException {
  Term term = new Term(featureField, featureName);
  TermStates states = TermStates.build(reader.getContext(), term, true);
  if (states.docFreq() == 0) {
    // avoid division by 0
    // The return value doesn't matter much here, the term doesn't exist,
    // it will never be used for scoring. Just Make sure to return a legal
    // value.
    return 1;
  }
  float avgFreq = (float) ((double) states.totalTermFreq() / states.docFreq());
  return decodeFeatureValue(avgFreq);
}
 

@Override
public Weight createWeight(final IndexSearcher searcher, final ScoreMode scoreMode, final float boost)
        throws IOException {
    final IndexReaderContext context = searcher.getTopReaderContext();
    final TermStates termState = TermStates.build(context, term, scoreMode.needsScores());
    // TODO: set boosts to 1f if needsScores is false?
    return new FieldBoostWeight(termState, boost, fieldBoost.getBoost(term.field(), searcher.getIndexReader()));
}