Examples with SortedSetDocValuesField org.apache.lucene.document.SortedSetDocValuesField used on opensource projects

Example 46 with SortedSetDocValuesField

use of org.apache.lucene.document.SortedSetDocValuesField in project lucene-solr by apache.

the class TestSortedSetSelector method testMiddleMin.

public void testMiddleMin() throws Exception {
    Directory dir = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir);
    Document doc = new Document();
    doc.add(new SortedSetDocValuesField("value", new BytesRef("c")));
    doc.add(newStringField("id", "2", Field.Store.YES));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new SortedSetDocValuesField("value", new BytesRef("a")));
    doc.add(new SortedSetDocValuesField("value", new BytesRef("b")));
    doc.add(new SortedSetDocValuesField("value", new BytesRef("c")));
    doc.add(new SortedSetDocValuesField("value", new BytesRef("d")));
    doc.add(newStringField("id", "1", Field.Store.YES));
    writer.addDocument(doc);
    IndexReader ir = writer.getReader();
    writer.close();
    // slow wrapper does not support random access ordinals (there is no need for that!)
    IndexSearcher searcher = newSearcher(ir, false);
    Sort sort = new Sort(new SortedSetSortField("value", false, SortedSetSelector.Type.MIDDLE_MIN));
    TopDocs td = searcher.search(new MatchAllDocsQuery(), 10, sort);
    assertEquals(2, td.totalHits);
    // 'b' comes before 'c'
    assertEquals("1", searcher.doc(td.scoreDocs[0].doc).get("id"));
    assertEquals("2", searcher.doc(td.scoreDocs[1].doc).get("id"));
    ir.close();
    dir.close();
}

Example 47 with SortedSetDocValuesField

use of org.apache.lucene.document.SortedSetDocValuesField in project lucene-solr by apache.

the class TestMemoryIndexAgainstRAMDir method testDocValuesMemoryIndexVsNormalIndex.

public void testDocValuesMemoryIndexVsNormalIndex() throws Exception {
    Document doc = new Document();
    long randomLong = random().nextLong();
    doc.add(new NumericDocValuesField("numeric", randomLong));
    int numValues = atLeast(5);
    for (int i = 0; i < numValues; i++) {
        randomLong = random().nextLong();
        doc.add(new SortedNumericDocValuesField("sorted_numeric", randomLong));
        if (random().nextBoolean()) {
            // randomly duplicate field/value
            doc.add(new SortedNumericDocValuesField("sorted_numeric", randomLong));
        }
    }
    BytesRef randomTerm = new BytesRef(randomTerm());
    doc.add(new BinaryDocValuesField("binary", randomTerm));
    if (random().nextBoolean()) {
        doc.add(new StringField("binary", randomTerm, Field.Store.NO));
    }
    randomTerm = new BytesRef(randomTerm());
    doc.add(new SortedDocValuesField("sorted", randomTerm));
    if (random().nextBoolean()) {
        doc.add(new StringField("sorted", randomTerm, Field.Store.NO));
    }
    numValues = atLeast(5);
    for (int i = 0; i < numValues; i++) {
        randomTerm = new BytesRef(randomTerm());
        doc.add(new SortedSetDocValuesField("sorted_set", randomTerm));
        if (random().nextBoolean()) {
            // randomly duplicate field/value
            doc.add(new SortedSetDocValuesField("sorted_set", randomTerm));
        }
        if (random().nextBoolean()) {
            // randomily just add a normal string field
            doc.add(new StringField("sorted_set", randomTerm, Field.Store.NO));
        }
    }
    MockAnalyzer mockAnalyzer = new MockAnalyzer(random());
    MemoryIndex memoryIndex = MemoryIndex.fromDocument(doc, mockAnalyzer);
    IndexReader indexReader = memoryIndex.createSearcher().getIndexReader();
    LeafReader leafReader = indexReader.leaves().get(0).reader();
    Directory dir = newDirectory();
    IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(random(), mockAnalyzer));
    writer.addDocument(doc);
    writer.close();
    IndexReader controlIndexReader = DirectoryReader.open(dir);
    LeafReader controlLeafReader = controlIndexReader.leaves().get(0).reader();
    NumericDocValues numericDocValues = leafReader.getNumericDocValues("numeric");
    NumericDocValues controlNumericDocValues = controlLeafReader.getNumericDocValues("numeric");
    assertEquals(0, numericDocValues.nextDoc());
    assertEquals(0, controlNumericDocValues.nextDoc());
    assertEquals(controlNumericDocValues.longValue(), numericDocValues.longValue());
    SortedNumericDocValues sortedNumericDocValues = leafReader.getSortedNumericDocValues("sorted_numeric");
    assertEquals(0, sortedNumericDocValues.nextDoc());
    SortedNumericDocValues controlSortedNumericDocValues = controlLeafReader.getSortedNumericDocValues("sorted_numeric");
    assertEquals(0, controlSortedNumericDocValues.nextDoc());
    assertEquals(controlSortedNumericDocValues.docValueCount(), sortedNumericDocValues.docValueCount());
    for (int i = 0; i < controlSortedNumericDocValues.docValueCount(); i++) {
        assertEquals(controlSortedNumericDocValues.nextValue(), sortedNumericDocValues.nextValue());
    }
    BinaryDocValues binaryDocValues = leafReader.getBinaryDocValues("binary");
    BinaryDocValues controlBinaryDocValues = controlLeafReader.getBinaryDocValues("binary");
    assertEquals(0, binaryDocValues.nextDoc());
    assertEquals(0, controlBinaryDocValues.nextDoc());
    assertEquals(controlBinaryDocValues.binaryValue(), binaryDocValues.binaryValue());
    SortedDocValues sortedDocValues = leafReader.getSortedDocValues("sorted");
    SortedDocValues controlSortedDocValues = controlLeafReader.getSortedDocValues("sorted");
    assertEquals(controlSortedDocValues.getValueCount(), sortedDocValues.getValueCount());
    assertEquals(0, sortedDocValues.nextDoc());
    assertEquals(0, controlSortedDocValues.nextDoc());
    assertEquals(controlSortedDocValues.binaryValue(), sortedDocValues.binaryValue());
    assertEquals(controlSortedDocValues.ordValue(), sortedDocValues.ordValue());
    assertEquals(controlSortedDocValues.lookupOrd(0), sortedDocValues.lookupOrd(0));
    SortedSetDocValues sortedSetDocValues = leafReader.getSortedSetDocValues("sorted_set");
    assertEquals(0, sortedSetDocValues.nextDoc());
    SortedSetDocValues controlSortedSetDocValues = controlLeafReader.getSortedSetDocValues("sorted_set");
    assertEquals(0, controlSortedSetDocValues.nextDoc());
    assertEquals(controlSortedSetDocValues.getValueCount(), sortedSetDocValues.getValueCount());
    for (long controlOrd = controlSortedSetDocValues.nextOrd(); controlOrd != SortedSetDocValues.NO_MORE_ORDS; controlOrd = controlSortedSetDocValues.nextOrd()) {
        assertEquals(controlOrd, sortedSetDocValues.nextOrd());
        assertEquals(controlSortedSetDocValues.lookupOrd(controlOrd), sortedSetDocValues.lookupOrd(controlOrd));
    }
    assertEquals(SortedSetDocValues.NO_MORE_ORDS, sortedSetDocValues.nextOrd());
    indexReader.close();
    controlIndexReader.close();
    dir.close();
}

Example 48 with SortedSetDocValuesField

use of org.apache.lucene.document.SortedSetDocValuesField in project lucene-solr by apache.

the class TestJoinUtil method test300spartans.

void test300spartans(boolean multipleValues, ScoreMode scoreMode) throws Exception {
    final String idField = "id";
    final String toField = "productId";
    Directory dir = newDirectory();
    RandomIndexWriter w = new RandomIndexWriter(random(), dir, newIndexWriterConfig(new MockAnalyzer(random())).setMergePolicy(newLogMergePolicy()));
    // 0
    Document doc = new Document();
    doc.add(new TextField("description", "random text", Field.Store.NO));
    doc.add(new TextField("name", "name1", Field.Store.NO));
    doc.add(new TextField(idField, "0", Field.Store.NO));
    doc.add(new SortedDocValuesField(idField, new BytesRef("0")));
    w.addDocument(doc);
    doc = new Document();
    doc.add(new TextField("price", "10.0", Field.Store.NO));
    if (multipleValues) {
        for (int i = 0; i < 300; i++) {
            doc.add(new SortedSetDocValuesField(toField, new BytesRef("" + i)));
        }
    } else {
        doc.add(new SortedDocValuesField(toField, new BytesRef("0")));
    }
    w.addDocument(doc);
    IndexSearcher indexSearcher = new IndexSearcher(w.getReader());
    w.close();
    // Search for product
    Query joinQuery = JoinUtil.createJoinQuery(toField, multipleValues, idField, new TermQuery(new Term("price", "10.0")), indexSearcher, scoreMode);
    TopDocs result = indexSearcher.search(joinQuery, 10);
    assertEquals(1, result.totalHits);
    assertEquals(0, result.scoreDocs[0].doc);
    indexSearcher.getIndexReader().close();
    dir.close();
}

Example 49 with SortedSetDocValuesField

use of org.apache.lucene.document.SortedSetDocValuesField in project lucene-solr by apache.

the class BaseDocValuesFormatTestCase method testSortedSetTwoDocumentsMerged.

public void testSortedSetTwoDocumentsMerged() throws IOException {
    Directory directory = newDirectory();
    Analyzer analyzer = new MockAnalyzer(random());
    IndexWriterConfig iwconfig = newIndexWriterConfig(analyzer);
    iwconfig.setMergePolicy(newLogMergePolicy());
    RandomIndexWriter iwriter = new RandomIndexWriter(random(), directory, iwconfig);
    Document doc = new Document();
    doc.add(new SortedSetDocValuesField("field", new BytesRef("hello")));
    iwriter.addDocument(doc);
    iwriter.commit();
    doc = new Document();
    doc.add(new SortedSetDocValuesField("field", new BytesRef("world")));
    iwriter.addDocument(doc);
    iwriter.forceMerge(1);
    DirectoryReader ireader = iwriter.getReader();
    iwriter.close();
    SortedSetDocValues dv = getOnlyLeafReader(ireader).getSortedSetDocValues("field");
    assertEquals(2, dv.getValueCount());
    assertEquals(0, dv.nextDoc());
    assertEquals(0, dv.nextOrd());
    assertEquals(NO_MORE_ORDS, dv.nextOrd());
    BytesRef bytes = dv.lookupOrd(0);
    assertEquals(new BytesRef("hello"), bytes);
    assertEquals(1, dv.nextDoc());
    assertEquals(1, dv.nextOrd());
    assertEquals(NO_MORE_ORDS, dv.nextOrd());
    bytes = dv.lookupOrd(1);
    assertEquals(new BytesRef("world"), bytes);
    ireader.close();
    directory.close();
}

Example 50 with SortedSetDocValuesField

use of org.apache.lucene.document.SortedSetDocValuesField in project lucene-solr by apache.

the class BaseDocValuesFormatTestCase method testSortedSetThreeValuesTwoDocs.

public void testSortedSetThreeValuesTwoDocs() throws IOException {
    Directory directory = newDirectory();
    Analyzer analyzer = new MockAnalyzer(random());
    IndexWriterConfig iwconfig = newIndexWriterConfig(analyzer);
    iwconfig.setMergePolicy(newLogMergePolicy());
    RandomIndexWriter iwriter = new RandomIndexWriter(random(), directory, iwconfig);
    Document doc = new Document();
    doc.add(new SortedSetDocValuesField("field", new BytesRef("hello")));
    doc.add(new SortedSetDocValuesField("field", new BytesRef("world")));
    iwriter.addDocument(doc);
    iwriter.commit();
    doc = new Document();
    doc.add(new SortedSetDocValuesField("field", new BytesRef("hello")));
    doc.add(new SortedSetDocValuesField("field", new BytesRef("beer")));
    iwriter.addDocument(doc);
    iwriter.forceMerge(1);
    DirectoryReader ireader = iwriter.getReader();
    iwriter.close();
    SortedSetDocValues dv = getOnlyLeafReader(ireader).getSortedSetDocValues("field");
    assertEquals(3, dv.getValueCount());
    assertEquals(0, dv.nextDoc());
    assertEquals(1, dv.nextOrd());
    assertEquals(2, dv.nextOrd());
    assertEquals(NO_MORE_ORDS, dv.nextOrd());
    assertEquals(1, dv.nextDoc());
    assertEquals(0, dv.nextOrd());
    assertEquals(1, dv.nextOrd());
    assertEquals(NO_MORE_ORDS, dv.nextOrd());
    BytesRef bytes = dv.lookupOrd(0);
    assertEquals(new BytesRef("beer"), bytes);
    bytes = dv.lookupOrd(1);
    assertEquals(new BytesRef("hello"), bytes);
    bytes = dv.lookupOrd(2);
    assertEquals(new BytesRef("world"), bytes);
    ireader.close();
    directory.close();
}