Examples with TermState org.apache.lucene.index.TermState used on opensource projects

Example 6 with TermState

use of org.apache.lucene.index.TermState in project elasticsearch by elastic.

the class BlendedTermQuery method adjustTTF.

private TermContext adjustTTF(IndexReaderContext readerContext, TermContext termContext, long sumTTF) {
    assert termContext.wasBuiltFor(readerContext);
    if (sumTTF == -1 && termContext.totalTermFreq() == -1) {
        return termContext;
    }
    TermContext newTermContext = new TermContext(readerContext);
    List<LeafReaderContext> leaves = readerContext.leaves();
    final int len;
    if (leaves == null) {
        len = 1;
    } else {
        len = leaves.size();
    }
    int df = termContext.docFreq();
    long ttf = sumTTF;
    for (int i = 0; i < len; i++) {
        TermState termState = termContext.get(i);
        if (termState == null) {
            continue;
        }
        newTermContext.register(termState, i, df, ttf);
        df = 0;
        ttf = 0;
    }
    return newTermContext;
}

Example 7 with TermState

use of org.apache.lucene.index.TermState in project elasticsearch by elastic.

the class AllTermQuery method createWeight.

@Override
public Weight createWeight(IndexSearcher searcher, boolean needsScores) throws IOException {
    if (needsScores == false) {
        return new TermQuery(term).createWeight(searcher, needsScores);
    }
    final TermContext termStates = TermContext.build(searcher.getTopReaderContext(), term);
    final CollectionStatistics collectionStats = searcher.collectionStatistics(term.field());
    final TermStatistics termStats = searcher.termStatistics(term, termStates);
    final Similarity similarity = searcher.getSimilarity(needsScores);
    final SimWeight stats = similarity.computeWeight(collectionStats, termStats);
    return new Weight(this) {

        @Override
        public float getValueForNormalization() throws IOException {
            return stats.getValueForNormalization();
        }

        @Override
        public void normalize(float norm, float topLevelBoost) {
            stats.normalize(norm, topLevelBoost);
        }

        @Override
        public void extractTerms(Set<Term> terms) {
            terms.add(term);
        }

        @Override
        public Explanation explain(LeafReaderContext context, int doc) throws IOException {
            AllTermScorer scorer = scorer(context);
            if (scorer != null) {
                int newDoc = scorer.iterator().advance(doc);
                if (newDoc == doc) {
                    float score = scorer.score();
                    float freq = scorer.freq();
                    SimScorer docScorer = similarity.simScorer(stats, context);
                    Explanation freqExplanation = Explanation.match(freq, "termFreq=" + freq);
                    Explanation termScoreExplanation = docScorer.explain(doc, freqExplanation);
                    Explanation payloadBoostExplanation = Explanation.match(scorer.payloadBoost(), "payloadBoost=" + scorer.payloadBoost());
                    return Explanation.match(score, "weight(" + getQuery() + " in " + doc + ") [" + similarity.getClass().getSimpleName() + "], product of:", termScoreExplanation, payloadBoostExplanation);
                }
            }
            return Explanation.noMatch("no matching term");
        }

        @Override
        public AllTermScorer scorer(LeafReaderContext context) throws IOException {
            final Terms terms = context.reader().terms(term.field());
            if (terms == null) {
                return null;
            }
            final TermsEnum termsEnum = terms.iterator();
            if (termsEnum == null) {
                return null;
            }
            final TermState state = termStates.get(context.ord);
            if (state == null) {
                // Term does not exist in this segment
                return null;
            }
            termsEnum.seekExact(term.bytes(), state);
            PostingsEnum docs = termsEnum.postings(null, PostingsEnum.PAYLOADS);
            assert docs != null;
            return new AllTermScorer(this, docs, similarity.simScorer(stats, context));
        }
    };
}

Example 8 with TermState

use of org.apache.lucene.index.TermState in project lucene-solr by apache.

the class SegmentTermsEnum method termState.

@Override
public TermState termState() throws IOException {
    assert !eof;
    currentFrame.decodeMetaData();
    TermState ts = currentFrame.state.clone();
    //if (DEBUG) System.out.println("BTTR.termState seg=" + segment + " state=" + ts);
    return ts;
}

Example 9 with TermState

use of org.apache.lucene.index.TermState in project lucene-solr by apache.

the class MultiTermQueryConstantScoreWrapper method createWeight.

@Override
public Weight createWeight(IndexSearcher searcher, boolean needsScores, float boost) throws IOException {
    return new ConstantScoreWeight(this, boost) {

        /** Try to collect terms from the given terms enum and return true iff all
       *  terms could be collected. If {@code false} is returned, the enum is
       *  left positioned on the next term. */
        private boolean collectTerms(LeafReaderContext context, TermsEnum termsEnum, List<TermAndState> terms) throws IOException {
            final int threshold = Math.min(BOOLEAN_REWRITE_TERM_COUNT_THRESHOLD, BooleanQuery.getMaxClauseCount());
            for (int i = 0; i < threshold; ++i) {
                final BytesRef term = termsEnum.next();
                if (term == null) {
                    return true;
                }
                TermState state = termsEnum.termState();
                terms.add(new TermAndState(BytesRef.deepCopyOf(term), state, termsEnum.docFreq(), termsEnum.totalTermFreq()));
            }
            return termsEnum.next() == null;
        }

        /**
       * On the given leaf context, try to either rewrite to a disjunction if
       * there are few terms, or build a bitset containing matching docs.
       */
        private WeightOrDocIdSet rewrite(LeafReaderContext context) throws IOException {
            final Terms terms = context.reader().terms(query.field);
            if (terms == null) {
                // field does not exist
                return new WeightOrDocIdSet((DocIdSet) null);
            }
            final TermsEnum termsEnum = query.getTermsEnum(terms);
            assert termsEnum != null;
            PostingsEnum docs = null;
            final List<TermAndState> collectedTerms = new ArrayList<>();
            if (collectTerms(context, termsEnum, collectedTerms)) {
                // build a boolean query
                BooleanQuery.Builder bq = new BooleanQuery.Builder();
                for (TermAndState t : collectedTerms) {
                    final TermContext termContext = new TermContext(searcher.getTopReaderContext());
                    termContext.register(t.state, context.ord, t.docFreq, t.totalTermFreq);
                    bq.add(new TermQuery(new Term(query.field, t.term), termContext), Occur.SHOULD);
                }
                Query q = new ConstantScoreQuery(bq.build());
                final Weight weight = searcher.rewrite(q).createWeight(searcher, needsScores, score());
                return new WeightOrDocIdSet(weight);
            }
            // Too many terms: go back to the terms we already collected and start building the bit set
            DocIdSetBuilder builder = new DocIdSetBuilder(context.reader().maxDoc(), terms);
            if (collectedTerms.isEmpty() == false) {
                TermsEnum termsEnum2 = terms.iterator();
                for (TermAndState t : collectedTerms) {
                    termsEnum2.seekExact(t.term, t.state);
                    docs = termsEnum2.postings(docs, PostingsEnum.NONE);
                    builder.add(docs);
                }
            }
            // Then keep filling the bit set with remaining terms
            do {
                docs = termsEnum.postings(docs, PostingsEnum.NONE);
                builder.add(docs);
            } while (termsEnum.next() != null);
            return new WeightOrDocIdSet(builder.build());
        }

        private Scorer scorer(DocIdSet set) throws IOException {
            if (set == null) {
                return null;
            }
            final DocIdSetIterator disi = set.iterator();
            if (disi == null) {
                return null;
            }
            return new ConstantScoreScorer(this, score(), disi);
        }

        @Override
        public BulkScorer bulkScorer(LeafReaderContext context) throws IOException {
            final WeightOrDocIdSet weightOrBitSet = rewrite(context);
            if (weightOrBitSet.weight != null) {
                return weightOrBitSet.weight.bulkScorer(context);
            } else {
                final Scorer scorer = scorer(weightOrBitSet.set);
                if (scorer == null) {
                    return null;
                }
                return new DefaultBulkScorer(scorer);
            }
        }

        @Override
        public Scorer scorer(LeafReaderContext context) throws IOException {
            final WeightOrDocIdSet weightOrBitSet = rewrite(context);
            if (weightOrBitSet.weight != null) {
                return weightOrBitSet.weight.scorer(context);
            } else {
                return scorer(weightOrBitSet.set);
            }
        }
    };
}

Example 10 with TermState

use of org.apache.lucene.index.TermState in project crate by crate.

the class BlendedTermQuery method adjustTTF.

private TermStates adjustTTF(IndexReaderContext readerContext, TermStates termContext, long sumTTF) throws IOException {
    assert termContext.wasBuiltFor(readerContext);
    if (sumTTF == -1 && termContext.totalTermFreq() == -1) {
        return termContext;
    }
    TermStates newTermContext = new TermStates(readerContext);
    List<LeafReaderContext> leaves = readerContext.leaves();
    final int len;
    if (leaves == null) {
        len = 1;
    } else {
        len = leaves.size();
    }
    int df = termContext.docFreq();
    long ttf = sumTTF;
    if (leaves != null) {
        for (int i = 0; i < len; i++) {
            TermState termState = termContext.get(leaves.get(i));
            if (termState == null) {
                continue;
            }
            newTermContext.register(termState, i, df, ttf);
            df = 0;
            ttf = 0;
        }
    }
    return newTermContext;
}