Examples with SimpleCollector org.apache.lucene.search.SimpleCollector used on opensource projects

Example 11 with SimpleCollector

use of org.apache.lucene.search.SimpleCollector in project lucene-solr by apache.

the class HighlighterPhraseTest method testConcurrentSpan.

public void testConcurrentSpan() throws IOException, InvalidTokenOffsetsException {
    final String TEXT = "the fox jumped";
    final Directory directory = newDirectory();
    final IndexWriter indexWriter = new IndexWriter(directory, newIndexWriterConfig(new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false)));
    try {
        final Document document = new Document();
        FieldType customType = new FieldType(TextField.TYPE_NOT_STORED);
        customType.setStoreTermVectorOffsets(true);
        customType.setStoreTermVectorPositions(true);
        customType.setStoreTermVectors(true);
        document.add(new Field(FIELD, new TokenStreamConcurrent(), customType));
        indexWriter.addDocument(document);
    } finally {
        indexWriter.close();
    }
    final IndexReader indexReader = DirectoryReader.open(directory);
    try {
        assertEquals(1, indexReader.numDocs());
        final IndexSearcher indexSearcher = newSearcher(indexReader);
        final Query phraseQuery = new SpanNearQuery(new SpanQuery[] { new SpanTermQuery(new Term(FIELD, "fox")), new SpanTermQuery(new Term(FIELD, "jumped")) }, 0, true);
        final FixedBitSet bitset = new FixedBitSet(indexReader.maxDoc());
        indexSearcher.search(phraseQuery, new SimpleCollector() {

            private int baseDoc;

            @Override
            public void collect(int i) {
                bitset.set(this.baseDoc + i);
            }

            @Override
            protected void doSetNextReader(LeafReaderContext context) throws IOException {
                this.baseDoc = context.docBase;
            }

            @Override
            public void setScorer(org.apache.lucene.search.Scorer scorer) {
            // Do Nothing
            }

            @Override
            public boolean needsScores() {
                return false;
            }
        });
        assertEquals(1, bitset.cardinality());
        final int maxDoc = indexReader.maxDoc();
        final Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(), new SimpleHTMLEncoder(), new QueryScorer(phraseQuery));
        for (int position = bitset.nextSetBit(0); position < maxDoc - 1; position = bitset.nextSetBit(position + 1)) {
            assertEquals(0, position);
            final TokenStream tokenStream = TokenSources.getTermVectorTokenStreamOrNull(FIELD, indexReader.getTermVectors(position), -1);
            assertEquals(highlighter.getBestFragment(new TokenStreamConcurrent(), TEXT), highlighter.getBestFragment(tokenStream, TEXT));
        }
    } finally {
        indexReader.close();
        directory.close();
    }
}

Example 12 with SimpleCollector

use of org.apache.lucene.search.SimpleCollector in project lucene-solr by apache.

the class JoinUtil method createJoinQuery.

/**
   * Method for query time joining for numeric fields. It supports multi- and single- values longs, ints, floats and longs.
   * All considerations from {@link JoinUtil#createJoinQuery(String, boolean, String, Query, IndexSearcher, ScoreMode)} are applicable here too,
   * though memory consumption might be higher.
   * <p>
   *
   * @param fromField                 The from field to join from
   * @param multipleValuesPerDocument Whether the from field has multiple terms per document
   *                                  when true fromField might be {@link DocValuesType#SORTED_NUMERIC},
   *                                  otherwise fromField should be {@link DocValuesType#NUMERIC}
   * @param toField                   The to field to join to, should be {@link IntPoint}, {@link LongPoint}, {@link FloatPoint}
   *                                  or {@link DoublePoint}.
   * @param numericType               either {@link java.lang.Integer}, {@link java.lang.Long}, {@link java.lang.Float}
   *                                  or {@link java.lang.Double} it should correspond to toField types
   * @param fromQuery                 The query to match documents on the from side
   * @param fromSearcher              The searcher that executed the specified fromQuery
   * @param scoreMode                 Instructs how scores from the fromQuery are mapped to the returned query
   * @return a {@link Query} instance that can be used to join documents based on the
   *         terms in the from and to field
   * @throws IOException If I/O related errors occur
   */
public static Query createJoinQuery(String fromField, boolean multipleValuesPerDocument, String toField, Class<? extends Number> numericType, Query fromQuery, IndexSearcher fromSearcher, ScoreMode scoreMode) throws IOException {
    TreeSet<Long> joinValues = new TreeSet<>();
    Map<Long, Float> aggregatedScores = new HashMap<>();
    Map<Long, Integer> occurrences = new HashMap<>();
    boolean needsScore = scoreMode != ScoreMode.None;
    BiConsumer<Long, Float> scoreAggregator;
    if (scoreMode == ScoreMode.Max) {
        scoreAggregator = (key, score) -> {
            Float currentValue = aggregatedScores.putIfAbsent(key, score);
            if (currentValue != null) {
                aggregatedScores.put(key, Math.max(currentValue, score));
            }
        };
    } else if (scoreMode == ScoreMode.Min) {
        scoreAggregator = (key, score) -> {
            Float currentValue = aggregatedScores.putIfAbsent(key, score);
            if (currentValue != null) {
                aggregatedScores.put(key, Math.min(currentValue, score));
            }
        };
    } else if (scoreMode == ScoreMode.Total) {
        scoreAggregator = (key, score) -> {
            Float currentValue = aggregatedScores.putIfAbsent(key, score);
            if (currentValue != null) {
                aggregatedScores.put(key, currentValue + score);
            }
        };
    } else if (scoreMode == ScoreMode.Avg) {
        scoreAggregator = (key, score) -> {
            Float currentSore = aggregatedScores.putIfAbsent(key, score);
            if (currentSore != null) {
                aggregatedScores.put(key, currentSore + score);
            }
            Integer currentOccurrence = occurrences.putIfAbsent(key, 1);
            if (currentOccurrence != null) {
                occurrences.put(key, ++currentOccurrence);
            }
        };
    } else {
        scoreAggregator = (key, score) -> {
            throw new UnsupportedOperationException();
        };
    }
    LongFunction<Float> joinScorer;
    if (scoreMode == ScoreMode.Avg) {
        joinScorer = (joinValue) -> {
            Float aggregatedScore = aggregatedScores.get(joinValue);
            Integer occurrence = occurrences.get(joinValue);
            return aggregatedScore / occurrence;
        };
    } else {
        joinScorer = aggregatedScores::get;
    }
    Collector collector;
    if (multipleValuesPerDocument) {
        collector = new SimpleCollector() {

            SortedNumericDocValues sortedNumericDocValues;

            Scorer scorer;

            @Override
            public void collect(int doc) throws IOException {
                if (doc > sortedNumericDocValues.docID()) {
                    sortedNumericDocValues.advance(doc);
                }
                if (doc == sortedNumericDocValues.docID()) {
                    for (int i = 0; i < sortedNumericDocValues.docValueCount(); i++) {
                        long value = sortedNumericDocValues.nextValue();
                        joinValues.add(value);
                        if (needsScore) {
                            scoreAggregator.accept(value, scorer.score());
                        }
                    }
                }
            }

            @Override
            protected void doSetNextReader(LeafReaderContext context) throws IOException {
                sortedNumericDocValues = DocValues.getSortedNumeric(context.reader(), fromField);
            }

            @Override
            public void setScorer(Scorer scorer) throws IOException {
                this.scorer = scorer;
            }

            @Override
            public boolean needsScores() {
                return needsScore;
            }
        };
    } else {
        collector = new SimpleCollector() {

            NumericDocValues numericDocValues;

            Scorer scorer;

            private int lastDocID = -1;

            private boolean docsInOrder(int docID) {
                if (docID < lastDocID) {
                    throw new AssertionError("docs out of order: lastDocID=" + lastDocID + " vs docID=" + docID);
                }
                lastDocID = docID;
                return true;
            }

            @Override
            public void collect(int doc) throws IOException {
                assert docsInOrder(doc);
                int dvDocID = numericDocValues.docID();
                if (dvDocID < doc) {
                    dvDocID = numericDocValues.advance(doc);
                }
                long value;
                if (dvDocID == doc) {
                    value = numericDocValues.longValue();
                } else {
                    value = 0;
                }
                joinValues.add(value);
                if (needsScore) {
                    scoreAggregator.accept(value, scorer.score());
                }
            }

            @Override
            protected void doSetNextReader(LeafReaderContext context) throws IOException {
                numericDocValues = DocValues.getNumeric(context.reader(), fromField);
                lastDocID = -1;
            }

            @Override
            public void setScorer(Scorer scorer) throws IOException {
                this.scorer = scorer;
            }

            @Override
            public boolean needsScores() {
                return needsScore;
            }
        };
    }
    fromSearcher.search(fromQuery, collector);
    Iterator<Long> iterator = joinValues.iterator();
    final int bytesPerDim;
    final BytesRef encoded = new BytesRef();
    final PointInSetIncludingScoreQuery.Stream stream;
    if (Integer.class.equals(numericType)) {
        bytesPerDim = Integer.BYTES;
        stream = new PointInSetIncludingScoreQuery.Stream() {

            @Override
            public BytesRef next() {
                if (iterator.hasNext()) {
                    long value = iterator.next();
                    IntPoint.encodeDimension((int) value, encoded.bytes, 0);
                    if (needsScore) {
                        score = joinScorer.apply(value);
                    }
                    return encoded;
                } else {
                    return null;
                }
            }
        };
    } else if (Long.class.equals(numericType)) {
        bytesPerDim = Long.BYTES;
        stream = new PointInSetIncludingScoreQuery.Stream() {

            @Override
            public BytesRef next() {
                if (iterator.hasNext()) {
                    long value = iterator.next();
                    LongPoint.encodeDimension(value, encoded.bytes, 0);
                    if (needsScore) {
                        score = joinScorer.apply(value);
                    }
                    return encoded;
                } else {
                    return null;
                }
            }
        };
    } else if (Float.class.equals(numericType)) {
        bytesPerDim = Float.BYTES;
        stream = new PointInSetIncludingScoreQuery.Stream() {

            @Override
            public BytesRef next() {
                if (iterator.hasNext()) {
                    long value = iterator.next();
                    FloatPoint.encodeDimension(Float.intBitsToFloat((int) value), encoded.bytes, 0);
                    if (needsScore) {
                        score = joinScorer.apply(value);
                    }
                    return encoded;
                } else {
                    return null;
                }
            }
        };
    } else if (Double.class.equals(numericType)) {
        bytesPerDim = Double.BYTES;
        stream = new PointInSetIncludingScoreQuery.Stream() {

            @Override
            public BytesRef next() {
                if (iterator.hasNext()) {
                    long value = iterator.next();
                    DoublePoint.encodeDimension(Double.longBitsToDouble(value), encoded.bytes, 0);
                    if (needsScore) {
                        score = joinScorer.apply(value);
                    }
                    return encoded;
                } else {
                    return null;
                }
            }
        };
    } else {
        throw new IllegalArgumentException("unsupported numeric type, only Integer, Long, Float and Double are supported");
    }
    encoded.bytes = new byte[bytesPerDim];
    encoded.length = bytesPerDim;
    if (needsScore) {
        return new PointInSetIncludingScoreQuery(scoreMode, fromQuery, multipleValuesPerDocument, toField, bytesPerDim, stream) {

            @Override
            protected String toString(byte[] value) {
                return toString.apply(value, numericType);
            }
        };
    } else {
        return new PointInSetQuery(toField, 1, bytesPerDim, stream) {

            @Override
            protected String toString(byte[] value) {
                return PointInSetIncludingScoreQuery.toString.apply(value, numericType);
            }
        };
    }
}

Example 13 with SimpleCollector

use of org.apache.lucene.search.SimpleCollector in project lucene-solr by apache.

the class MemoryIndex method search.

/**
   * Convenience method that efficiently returns the relevance score by
   * matching this index against the given Lucene query expression.
   * 
   * @param query
   *            an arbitrary Lucene query to run against this index
   * @return the relevance score of the matchmaking; A number in the range
   *         [0.0 .. 1.0], with 0.0 indicating no match. The higher the number
   *         the better the match.
   *
   */
public float search(Query query) {
    if (query == null)
        throw new IllegalArgumentException("query must not be null");
    IndexSearcher searcher = createSearcher();
    try {
        // inits to 0.0f (no match)
        final float[] scores = new float[1];
        searcher.search(query, new SimpleCollector() {

            private Scorer scorer;

            @Override
            public void collect(int doc) throws IOException {
                scores[0] = scorer.score();
            }

            @Override
            public void setScorer(Scorer scorer) {
                this.scorer = scorer;
            }

            @Override
            public boolean needsScores() {
                return true;
            }
        });
        float score = scores[0];
        return score;
    } catch (IOException e) {
        // can never happen (RAMDirectory)
        throw new RuntimeException(e);
    }
}