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

Example 36 with LeafReader

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

the class PostingsWithTermVectorsOffsetStrategy method getOffsetsEnums.

@Override
public List<OffsetsEnum> getOffsetsEnums(IndexReader reader, int docId, String content) throws IOException {
    LeafReader leafReader;
    if (reader instanceof LeafReader) {
        leafReader = (LeafReader) reader;
    } else {
        List<LeafReaderContext> leaves = reader.leaves();
        LeafReaderContext LeafReaderContext = leaves.get(ReaderUtil.subIndex(docId, leaves));
        leafReader = LeafReaderContext.reader();
        // adjust 'doc' to be within this atomic reader
        docId -= LeafReaderContext.docBase;
    }
    Terms docTerms = leafReader.getTermVector(docId, field);
    if (docTerms == null) {
        return Collections.emptyList();
    }
    leafReader = new TermVectorFilteredLeafReader(leafReader, docTerms);
    return createOffsetsEnumsFromReader(leafReader, docId);
}

Example 37 with LeafReader

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

the class TermVectorOffsetStrategy method getOffsetsEnums.

@Override
public List<OffsetsEnum> getOffsetsEnums(IndexReader reader, int docId, String content) throws IOException {
    Terms tvTerms = reader.getTermVector(docId, field);
    if (tvTerms == null) {
        return Collections.emptyList();
    }
    LeafReader leafReader = new TermVectorLeafReader(field, tvTerms);
    docId = 0;
    return createOffsetsEnumsFromReader(leafReader, docId);
}

Example 38 with LeafReader

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

the class TestJoinUtil method testSimpleOrdinalsJoin.

public void testSimpleOrdinalsJoin() throws Exception {
    final String idField = "id";
    final String productIdField = "productId";
    // A field indicating to what type a document belongs, which is then used to distinques between documents during joining.
    final String typeField = "type";
    // A single sorted doc values field that holds the join values for all document types.
    // Typically during indexing a schema will automatically create this field with the values
    final String joinField = idField + productIdField;
    Directory dir = newDirectory();
    RandomIndexWriter w = new RandomIndexWriter(random(), dir, newIndexWriterConfig(new MockAnalyzer(random())).setMergePolicy(NoMergePolicy.INSTANCE));
    // 0
    Document doc = new Document();
    doc.add(new TextField(idField, "1", Field.Store.NO));
    doc.add(new TextField(typeField, "product", Field.Store.NO));
    doc.add(new TextField("description", "random text", Field.Store.NO));
    doc.add(new TextField("name", "name1", Field.Store.NO));
    doc.add(new SortedDocValuesField(joinField, new BytesRef("1")));
    w.addDocument(doc);
    // 1
    doc = new Document();
    doc.add(new TextField(productIdField, "1", Field.Store.NO));
    doc.add(new TextField(typeField, "price", Field.Store.NO));
    doc.add(new TextField("price", "10.0", Field.Store.NO));
    doc.add(new SortedDocValuesField(joinField, new BytesRef("1")));
    w.addDocument(doc);
    // 2
    doc = new Document();
    doc.add(new TextField(productIdField, "1", Field.Store.NO));
    doc.add(new TextField(typeField, "price", Field.Store.NO));
    doc.add(new TextField("price", "20.0", Field.Store.NO));
    doc.add(new SortedDocValuesField(joinField, new BytesRef("1")));
    w.addDocument(doc);
    // 3
    doc = new Document();
    doc.add(new TextField(idField, "2", Field.Store.NO));
    doc.add(new TextField(typeField, "product", Field.Store.NO));
    doc.add(new TextField("description", "more random text", Field.Store.NO));
    doc.add(new TextField("name", "name2", Field.Store.NO));
    doc.add(new SortedDocValuesField(joinField, new BytesRef("2")));
    w.addDocument(doc);
    w.commit();
    // 4
    doc = new Document();
    doc.add(new TextField(productIdField, "2", Field.Store.NO));
    doc.add(new TextField(typeField, "price", Field.Store.NO));
    doc.add(new TextField("price", "10.0", Field.Store.NO));
    doc.add(new SortedDocValuesField(joinField, new BytesRef("2")));
    w.addDocument(doc);
    // 5
    doc = new Document();
    doc.add(new TextField(productIdField, "2", Field.Store.NO));
    doc.add(new TextField(typeField, "price", Field.Store.NO));
    doc.add(new TextField("price", "20.0", Field.Store.NO));
    doc.add(new SortedDocValuesField(joinField, new BytesRef("2")));
    w.addDocument(doc);
    IndexSearcher indexSearcher = new IndexSearcher(w.getReader());
    w.close();
    IndexReader r = indexSearcher.getIndexReader();
    SortedDocValues[] values = new SortedDocValues[r.leaves().size()];
    for (int i = 0; i < values.length; i++) {
        LeafReader leafReader = r.leaves().get(i).reader();
        values[i] = DocValues.getSorted(leafReader, joinField);
    }
    MultiDocValues.OrdinalMap ordinalMap = MultiDocValues.OrdinalMap.build(null, values, PackedInts.DEFAULT);
    Query toQuery = new TermQuery(new Term(typeField, "price"));
    Query fromQuery = new TermQuery(new Term("name", "name2"));
    // Search for product and return prices
    Query joinQuery = JoinUtil.createJoinQuery(joinField, fromQuery, toQuery, indexSearcher, ScoreMode.None, ordinalMap);
    TopDocs result = indexSearcher.search(joinQuery, 10);
    assertEquals(2, result.totalHits);
    assertEquals(4, result.scoreDocs[0].doc);
    assertEquals(5, result.scoreDocs[1].doc);
    fromQuery = new TermQuery(new Term("name", "name1"));
    joinQuery = JoinUtil.createJoinQuery(joinField, fromQuery, toQuery, indexSearcher, ScoreMode.None, ordinalMap);
    result = indexSearcher.search(joinQuery, 10);
    assertEquals(2, result.totalHits);
    assertEquals(1, result.scoreDocs[0].doc);
    assertEquals(2, result.scoreDocs[1].doc);
    // Search for prices and return products
    fromQuery = new TermQuery(new Term("price", "20.0"));
    toQuery = new TermQuery(new Term(typeField, "product"));
    joinQuery = JoinUtil.createJoinQuery(joinField, fromQuery, toQuery, indexSearcher, ScoreMode.None, ordinalMap);
    result = indexSearcher.search(joinQuery, 10);
    assertEquals(2, result.totalHits);
    assertEquals(0, result.scoreDocs[0].doc);
    assertEquals(3, result.scoreDocs[1].doc);
    indexSearcher.getIndexReader().close();
    dir.close();
}

Example 39 with LeafReader

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

the class TestMemoryIndex method testSimilarities.

@Test
public void testSimilarities() throws IOException {
    MemoryIndex mi = new MemoryIndex();
    mi.addField("f1", "a long text field that contains many many terms", analyzer);
    IndexSearcher searcher = mi.createSearcher();
    LeafReader reader = (LeafReader) searcher.getIndexReader();
    NumericDocValues norms = reader.getNormValues("f1");
    assertEquals(0, norms.nextDoc());
    float n1 = norms.longValue();
    // Norms are re-computed when we change the Similarity
    mi.setSimilarity(new Similarity() {

        @Override
        public long computeNorm(FieldInvertState state) {
            return 74;
        }

        @Override
        public SimWeight computeWeight(float boost, CollectionStatistics collectionStats, TermStatistics... termStats) {
            throw new UnsupportedOperationException();
        }

        @Override
        public SimScorer simScorer(SimWeight weight, LeafReaderContext context) throws IOException {
            throw new UnsupportedOperationException();
        }
    });
    norms = reader.getNormValues("f1");
    assertEquals(0, norms.nextDoc());
    float n2 = norms.longValue();
    assertTrue(n1 != n2);
    TestUtil.checkReader(reader);
}

Example 40 with LeafReader

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

the class TestMemoryIndex method testDocValuesDoNotAffectBoostPositionsOrOffset.

public void testDocValuesDoNotAffectBoostPositionsOrOffset() throws Exception {
    Document doc = new Document();
    doc.add(new BinaryDocValuesField("text", new BytesRef("quick brown fox")));
    doc.add(new TextField("text", "quick brown fox", Field.Store.NO));
    MemoryIndex mi = MemoryIndex.fromDocument(doc, analyzer, true, true);
    LeafReader leafReader = mi.createSearcher().getIndexReader().leaves().get(0).reader();
    TermsEnum tenum = leafReader.terms("text").iterator();
    assertEquals("brown", tenum.next().utf8ToString());
    PostingsEnum penum = tenum.postings(null, PostingsEnum.OFFSETS);
    assertEquals(0, penum.nextDoc());
    assertEquals(1, penum.freq());
    assertEquals(1, penum.nextPosition());
    assertEquals(6, penum.startOffset());
    assertEquals(11, penum.endOffset());
    assertEquals("fox", tenum.next().utf8ToString());
    penum = tenum.postings(penum, PostingsEnum.OFFSETS);
    assertEquals(0, penum.nextDoc());
    assertEquals(1, penum.freq());
    assertEquals(2, penum.nextPosition());
    assertEquals(12, penum.startOffset());
    assertEquals(15, penum.endOffset());
    assertEquals("quick", tenum.next().utf8ToString());
    penum = tenum.postings(penum, PostingsEnum.OFFSETS);
    assertEquals(0, penum.nextDoc());
    assertEquals(1, penum.freq());
    assertEquals(0, penum.nextPosition());
    assertEquals(0, penum.startOffset());
    assertEquals(5, penum.endOffset());
    BinaryDocValues binaryDocValues = leafReader.getBinaryDocValues("text");
    assertEquals(0, binaryDocValues.nextDoc());
    assertEquals("quick brown fox", binaryDocValues.binaryValue().utf8ToString());
}