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

Example 1 with NumericDocValuesField

use of org.apache.lucene.document.NumericDocValuesField in project crate by crate.

the class OrderedLuceneBatchIteratorBenchmark method createLuceneBatchIterator.

@Setup
public void createLuceneBatchIterator() throws Exception {
    IndexWriter iw = new IndexWriter(new RAMDirectory(), new IndexWriterConfig(new StandardAnalyzer()));
    dummyShardId = new ShardId("dummy", 1);
    columnName = "x";
    for (int i = 0; i < 10_000_000; i++) {
        Document doc = new Document();
        doc.add(new NumericDocValuesField(columnName, i));
        iw.addDocument(doc);
    }
    iw.commit();
    iw.forceMerge(1, true);
    indexSearcher = new IndexSearcher(DirectoryReader.open(iw, true));
    collectorContext = new CollectorContext(mock(IndexFieldDataService.class), new CollectorFieldsVisitor(0));
    fieldTypeLookup = column -> {
        IntegerFieldMapper.IntegerFieldType integerFieldType = new IntegerFieldMapper.IntegerFieldType();
        integerFieldType.setNames(new MappedFieldType.Names(column));
        return integerFieldType;
    };
    reference = new Reference(new ReferenceIdent(new TableIdent(null, "dummyTable"), columnName), RowGranularity.DOC, DataTypes.INTEGER);
    orderBy = new OrderBy(Collections.singletonList(reference), reverseFlags, nullsFirst);
}

Example 2 with NumericDocValuesField

use of org.apache.lucene.document.NumericDocValuesField in project crate by crate.

the class BooleanColumnReferenceTest method insertValues.

@Override
protected void insertValues(IndexWriter writer) throws Exception {
    for (int i = 0; i < 10; i++) {
        Document doc = new Document();
        doc.add(new StringField("_id", Integer.toString(i), Field.Store.NO));
        doc.add(new NumericDocValuesField(column, i % 2 == 0 ? 1 : 0));
        writer.addDocument(doc);
    }
}

Example 3 with NumericDocValuesField

use of org.apache.lucene.document.NumericDocValuesField in project elasticsearch by elastic.

the class DiversifiedSamplerTests method testDiversifiedSampler.

public void testDiversifiedSampler() throws Exception {
    String[] data = { // "id,cat,name,price,inStock,author_t,series_t,sequence_i,genre_s,genre_id",
    "0553573403,book,A Game of Thrones,7.99,true,George R.R. Martin,A Song of Ice and Fire,1,fantasy,0", "0553579908,book,A Clash of Kings,7.99,true,George R.R. Martin,A Song of Ice and Fire,2,fantasy,0", "055357342X,book,A Storm of Swords,7.99,true,George R.R. Martin,A Song of Ice and Fire,3,fantasy,0", "0553293354,book,Foundation,17.99,true,Isaac Asimov,Foundation Novels,1,scifi,1", "0812521390,book,The Black Company,6.99,false,Glen Cook,The Chronicles of The Black Company,1,fantasy,0", "0812550706,book,Ender's Game,6.99,true,Orson Scott Card,Ender,1,scifi,1", "0441385532,book,Jhereg,7.95,false,Steven Brust,Vlad Taltos,1,fantasy,0", "0380014300,book,Nine Princes In Amber,6.99,true,Roger Zelazny,the Chronicles of Amber,1,fantasy,0", "0805080481,book,The Book of Three,5.99,true,Lloyd Alexander,The Chronicles of Prydain,1,fantasy,0", "080508049X,book,The Black Cauldron,5.99,true,Lloyd Alexander,The Chronicles of Prydain,2,fantasy,0" };
    Directory directory = newDirectory();
    RandomIndexWriter indexWriter = new RandomIndexWriter(random(), directory);
    for (String entry : data) {
        String[] parts = entry.split(",");
        Document document = new Document();
        document.add(new SortedDocValuesField("id", new BytesRef(parts[0])));
        document.add(new StringField("cat", parts[1], Field.Store.NO));
        document.add(new TextField("name", parts[2], Field.Store.NO));
        document.add(new DoubleDocValuesField("price", Double.valueOf(parts[3])));
        document.add(new StringField("inStock", parts[4], Field.Store.NO));
        document.add(new StringField("author", parts[5], Field.Store.NO));
        document.add(new StringField("series", parts[6], Field.Store.NO));
        document.add(new StringField("sequence", parts[7], Field.Store.NO));
        document.add(new SortedDocValuesField("genre", new BytesRef(parts[8])));
        document.add(new NumericDocValuesField("genre_id", Long.valueOf(parts[9])));
        indexWriter.addDocument(document);
    }
    indexWriter.close();
    IndexReader indexReader = DirectoryReader.open(directory);
    IndexSearcher indexSearcher = new IndexSearcher(indexReader);
    MappedFieldType genreFieldType = new KeywordFieldMapper.KeywordFieldType();
    genreFieldType.setName("genre");
    genreFieldType.setHasDocValues(true);
    Consumer<InternalSampler> verify = result -> {
        Terms terms = result.getAggregations().get("terms");
        assertEquals(2, terms.getBuckets().size());
        assertEquals("0805080481", terms.getBuckets().get(0).getKeyAsString());
        assertEquals("0812550706", terms.getBuckets().get(1).getKeyAsString());
    };
    testCase(indexSearcher, genreFieldType, "map", verify);
    testCase(indexSearcher, genreFieldType, "global_ordinals", verify);
    testCase(indexSearcher, genreFieldType, "bytes_hash", verify);
    genreFieldType = new NumberFieldMapper.NumberFieldType(NumberFieldMapper.NumberType.LONG);
    genreFieldType.setName("genre_id");
    testCase(indexSearcher, genreFieldType, null, verify);
    // wrong field:
    genreFieldType = new KeywordFieldMapper.KeywordFieldType();
    genreFieldType.setName("wrong_field");
    genreFieldType.setHasDocValues(true);
    testCase(indexSearcher, genreFieldType, null, result -> {
        Terms terms = result.getAggregations().get("terms");
        assertEquals(1, terms.getBuckets().size());
        assertEquals("0805080481", terms.getBuckets().get(0).getKeyAsString());
    });
    indexReader.close();
    directory.close();
}

Example 4 with NumericDocValuesField

use of org.apache.lucene.document.NumericDocValuesField in project elasticsearch by elastic.

the class SumAggregatorTests method testQueryFiltering.

public void testQueryFiltering() throws IOException {
    testCase(new TermQuery(new Term("match", "yes")), iw -> {
        iw.addDocument(Arrays.asList(new StringField("match", "yes", Field.Store.NO), new NumericDocValuesField(FIELD_NAME, 1)));
        iw.addDocument(Arrays.asList(new StringField("match", "no", Field.Store.NO), new NumericDocValuesField(FIELD_NAME, 2)));
        iw.addDocument(Arrays.asList(new StringField("match", "yes", Field.Store.NO), new NumericDocValuesField(FIELD_NAME, 3)));
        iw.addDocument(Arrays.asList(new StringField("match", "no", Field.Store.NO), new NumericDocValuesField(FIELD_NAME, 4)));
        iw.addDocument(Arrays.asList(new StringField("match", "yes", Field.Store.NO), new NumericDocValuesField(FIELD_NAME, 5)));
    }, count -> assertEquals(9L, count.getValue(), 0d));
}

Example 5 with NumericDocValuesField

use of org.apache.lucene.document.NumericDocValuesField in project elasticsearch by elastic.

the class AvgAggregatorTests method testSomeMatchesNumericDocValues.

public void testSomeMatchesNumericDocValues() throws IOException {
    testCase(new FieldValueQuery("number"), iw -> {
        iw.addDocument(singleton(new NumericDocValuesField("number", 7)));
        iw.addDocument(singleton(new NumericDocValuesField("number", 2)));
        iw.addDocument(singleton(new NumericDocValuesField("number", 3)));
    }, avg -> {
        assertEquals(4, avg.getValue(), 0);
    });
}