Example usage for org.apache.lucene.search CollectionStatistics sumDocFreq

Introduction

In this page you can find the example usage for org.apache.lucene.search CollectionStatistics sumDocFreq.

Prototype

long sumDocFreq

To view the source code for org.apache.lucene.search CollectionStatistics sumDocFreq.

Click Source Link

Usage

From source file:org.apache.solr.search.stats.CollectionStats.java

License:Apache License

public CollectionStats(CollectionStatistics stats) {
    this.field = stats.field();
    this.maxDoc = stats.maxDoc();
    this.docCount = stats.docCount();
    this.sumTotalTermFreq = stats.sumTotalTermFreq();
    this.sumDocFreq = stats.sumDocFreq();
}

---

From source file:org.elasticsearch.action.search.SearchPhaseController.java

License:Apache License

public AggregatedDfs aggregateDfs(AtomicArray<DfsSearchResult> results) {
    ObjectObjectHashMap<Term, TermStatistics> termStatistics = HppcMaps.newNoNullKeysMap();
    ObjectObjectHashMap<String, CollectionStatistics> fieldStatistics = HppcMaps.newNoNullKeysMap();
    long aggMaxDoc = 0;
    for (AtomicArray.Entry<DfsSearchResult> lEntry : results.asList()) {
        final Term[] terms = lEntry.value.terms();
        final TermStatistics[] stats = lEntry.value.termStatistics();
        assert terms.length == stats.length;
        for (int i = 0; i < terms.length; i++) {
            assert terms[i] != null;
            TermStatistics existing = termStatistics.get(terms[i]);
            if (existing != null) {
                assert terms[i].bytes().equals(existing.term());
                // totalTermFrequency is an optional statistic we need to check if either one or both
                // are set to -1 which means not present and then set it globally to -1
                termStatistics.put(terms[i],
                        new TermStatistics(existing.term(), existing.docFreq() + stats[i].docFreq(),
                                optionalSum(existing.totalTermFreq(), stats[i].totalTermFreq())));
            } else {
                termStatistics.put(terms[i], stats[i]);
            }/*www .  j  ava2 s.  co m*/

        }

        assert !lEntry.value.fieldStatistics().containsKey(null);
        final Object[] keys = lEntry.value.fieldStatistics().keys;
        final Object[] values = lEntry.value.fieldStatistics().values;
        for (int i = 0; i < keys.length; i++) {
            if (keys[i] != null) {
                String key = (String) keys[i];
                CollectionStatistics value = (CollectionStatistics) values[i];
                assert key != null;
                CollectionStatistics existing = fieldStatistics.get(key);
                if (existing != null) {
                    CollectionStatistics merged = new CollectionStatistics(key,
                            existing.maxDoc() + value.maxDoc(),
                            optionalSum(existing.docCount(), value.docCount()),
                            optionalSum(existing.sumTotalTermFreq(), value.sumTotalTermFreq()),
                            optionalSum(existing.sumDocFreq(), value.sumDocFreq()));
                    fieldStatistics.put(key, merged);
                } else {
                    fieldStatistics.put(key, value);
                }
            }
        }
        aggMaxDoc += lEntry.value.maxDoc();
    }
    return new AggregatedDfs(termStatistics, fieldStatistics, aggMaxDoc);
}

---

From source file:org.elasticsearch.action.termvectors.TermVectorsWriter.java

License:Apache License

private void writeFieldStatistics(CollectionStatistics fieldStats) throws IOException {
    long sttf = fieldStats.sumTotalTermFreq();
    assert (sttf >= -1);
    writePotentiallyNegativeVLong(sttf);
    long sdf = fieldStats.sumDocFreq();
    assert (sdf >= -1);
    writePotentiallyNegativeVLong(sdf);/*from  w ww. ja  va2 s  .  c  o m*/
    int dc = (int) fieldStats.docCount();
    assert (dc >= -1);
    writePotentiallyNegativeVInt(dc);
}

---

From source file:org.elasticsearch.index.similarity.ScriptedSimilarity.java

License:Apache License

@Override
public SimWeight computeWeight(float boost, CollectionStatistics collectionStats, TermStatistics... termStats) {
    Query query = new Query(boost);
    long docCount = collectionStats.docCount();
    if (docCount == -1) {
        docCount = collectionStats.maxDoc();
    }/*  w  w  w .  j a v a  2 s.  c o  m*/
    Field field = new Field(docCount, collectionStats.sumDocFreq(), collectionStats.sumTotalTermFreq());
    Term[] terms = new Term[termStats.length];
    for (int i = 0; i < termStats.length; ++i) {
        terms[i] = new Term(termStats[i].docFreq(), termStats[i].totalTermFreq());
    }
    return new Weight(collectionStats.field(), query, field, terms);
}

---

From source file:org.elasticsearch.search.controller.SearchPhaseController.java

License:Apache License

public AggregatedDfs aggregateDfs(AtomicArray<DfsSearchResult> results) {
    ObjectObjectOpenHashMap<Term, TermStatistics> termStatistics = HppcMaps.newNoNullKeysMap();
    ObjectObjectOpenHashMap<String, CollectionStatistics> fieldStatistics = HppcMaps.newNoNullKeysMap();
    long aggMaxDoc = 0;
    for (AtomicArray.Entry<DfsSearchResult> lEntry : results.asList()) {
        final Term[] terms = lEntry.value.terms();
        final TermStatistics[] stats = lEntry.value.termStatistics();
        assert terms.length == stats.length;
        for (int i = 0; i < terms.length; i++) {
            assert terms[i] != null;
            TermStatistics existing = termStatistics.get(terms[i]);
            if (existing != null) {
                assert terms[i].bytes().equals(existing.term());
                // totalTermFrequency is an optional statistic we need to check if either one or both
                // are set to -1 which means not present and then set it globally to -1
                termStatistics.put(terms[i],
                        new TermStatistics(existing.term(), existing.docFreq() + stats[i].docFreq(),
                                optionalSum(existing.totalTermFreq(), stats[i].totalTermFreq())));
            } else {
                termStatistics.put(terms[i], stats[i]);
            }//from   ww w.j  av a  2  s  . com

        }
        final boolean[] states = lEntry.value.fieldStatistics().allocated;
        final Object[] keys = lEntry.value.fieldStatistics().keys;
        final Object[] values = lEntry.value.fieldStatistics().values;
        for (int i = 0; i < states.length; i++) {
            if (states[i]) {
                String key = (String) keys[i];
                CollectionStatistics value = (CollectionStatistics) values[i];
                assert key != null;
                CollectionStatistics existing = fieldStatistics.get(key);
                if (existing != null) {
                    CollectionStatistics merged = new CollectionStatistics(key,
                            existing.maxDoc() + value.maxDoc(),
                            optionalSum(existing.docCount(), value.docCount()),
                            optionalSum(existing.sumTotalTermFreq(), value.sumTotalTermFreq()),
                            optionalSum(existing.sumDocFreq(), value.sumDocFreq()));
                    fieldStatistics.put(key, merged);
                } else {
                    fieldStatistics.put(key, value);
                }
            }
        }
        aggMaxDoc += lEntry.value.maxDoc();
    }
    return new AggregatedDfs(termStatistics, fieldStatistics, aggMaxDoc);
}

---

From source file:org.elasticsearch.search.dfs.DfsSearchResult.java

License:Apache License

public static void writeFieldStats(StreamOutput out,
        ObjectObjectOpenHashMap<String, CollectionStatistics> fieldStatistics) throws IOException {
    out.writeVInt(fieldStatistics.size());
    final boolean[] states = fieldStatistics.allocated;
    Object[] keys = fieldStatistics.keys;
    Object[] values = fieldStatistics.values;
    for (int i = 0; i < states.length; i++) {
        if (states[i]) {
            out.writeString((String) keys[i]);
            CollectionStatistics statistics = (CollectionStatistics) values[i];
            assert statistics.maxDoc() >= 0;
            out.writeVLong(statistics.maxDoc());
            out.writeVLong(addOne(statistics.docCount()));
            out.writeVLong(addOne(statistics.sumTotalTermFreq()));
            out.writeVLong(addOne(statistics.sumDocFreq()));
        }/*from   www .j  av  a 2  s .c om*/
    }
}

---