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

Example 36 with SortedSetDocValuesField

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

the class TestSortedSetSelector method testMaxMissingFirst.

public void testMaxMissingFirst() throws Exception {
    Directory dir = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir);
    Document doc = new Document();
    doc.add(newStringField("id", "1", Field.Store.YES));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new SortedSetDocValuesField("value", new BytesRef("foo")));
    doc.add(new SortedSetDocValuesField("value", new BytesRef("bar")));
    doc.add(newStringField("id", "2", Field.Store.YES));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new SortedSetDocValuesField("value", new BytesRef("baz")));
    doc.add(newStringField("id", "3", 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);
    SortField sortField = new SortedSetSortField("value", false, SortedSetSelector.Type.MAX);
    sortField.setMissingValue(SortField.STRING_FIRST);
    Sort sort = new Sort(sortField);
    TopDocs td = searcher.search(new MatchAllDocsQuery(), 10, sort);
    assertEquals(3, td.totalHits);
    // null comes first
    assertEquals("1", searcher.doc(td.scoreDocs[0].doc).get("id"));
    // 'baz' comes before 'foo'
    assertEquals("3", searcher.doc(td.scoreDocs[1].doc).get("id"));
    assertEquals("2", searcher.doc(td.scoreDocs[2].doc).get("id"));
    ir.close();
    dir.close();
}

Example 37 with SortedSetDocValuesField

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

the class TestSortedSetSelector method testMiddleMinMissingFirst.

public void testMiddleMinMissingFirst() throws Exception {
    Directory dir = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir);
    Document doc = new Document();
    doc.add(newStringField("id", "3", Field.Store.YES));
    writer.addDocument(doc);
    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);
    SortField sortField = new SortedSetSortField("value", false, SortedSetSelector.Type.MIDDLE_MIN);
    sortField.setMissingValue(SortField.STRING_FIRST);
    Sort sort = new Sort(sortField);
    TopDocs td = searcher.search(new MatchAllDocsQuery(), 10, sort);
    assertEquals(3, td.totalHits);
    // null comes first
    assertEquals("3", searcher.doc(td.scoreDocs[0].doc).get("id"));
    // 'b' comes before 'c'
    assertEquals("1", searcher.doc(td.scoreDocs[1].doc).get("id"));
    assertEquals("2", searcher.doc(td.scoreDocs[2].doc).get("id"));
    ir.close();
    dir.close();
}

Example 38 with SortedSetDocValuesField

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

the class TestSortedSetSortField method testSingleton.

public void testSingleton() throws Exception {
    Directory dir = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir);
    Document doc = new Document();
    doc.add(new SortedSetDocValuesField("value", new BytesRef("baz")));
    doc.add(newStringField("id", "2", Field.Store.YES));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new SortedSetDocValuesField("value", new BytesRef("bar")));
    doc.add(newStringField("id", "1", Field.Store.YES));
    writer.addDocument(doc);
    IndexReader ir = writer.getReader();
    writer.close();
    IndexSearcher searcher = newSearcher(ir);
    Sort sort = new Sort(new SortedSetSortField("value", false));
    TopDocs td = searcher.search(new MatchAllDocsQuery(), 10, sort);
    assertEquals(2, td.totalHits);
    // 'bar' comes before 'baz'
    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 39 with SortedSetDocValuesField

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

the class TestSortedSetSortField method testMissingFirst.

public void testMissingFirst() throws Exception {
    Directory dir = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), dir);
    Document doc = new Document();
    doc.add(new SortedSetDocValuesField("value", new BytesRef("baz")));
    doc.add(newStringField("id", "2", Field.Store.YES));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new SortedSetDocValuesField("value", new BytesRef("foo")));
    doc.add(new SortedSetDocValuesField("value", new BytesRef("bar")));
    doc.add(newStringField("id", "1", Field.Store.YES));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(newStringField("id", "3", Field.Store.YES));
    writer.addDocument(doc);
    IndexReader ir = writer.getReader();
    writer.close();
    IndexSearcher searcher = newSearcher(ir);
    SortField sortField = new SortedSetSortField("value", false);
    sortField.setMissingValue(SortField.STRING_FIRST);
    Sort sort = new Sort(sortField);
    TopDocs td = searcher.search(new MatchAllDocsQuery(), 10, sort);
    assertEquals(3, td.totalHits);
    // 'bar' comes before 'baz'
    // null comes first
    assertEquals("3", searcher.doc(td.scoreDocs[0].doc).get("id"));
    assertEquals("1", searcher.doc(td.scoreDocs[1].doc).get("id"));
    assertEquals("2", searcher.doc(td.scoreDocs[2].doc).get("id"));
    ir.close();
    dir.close();
}

Example 40 with SortedSetDocValuesField

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

the class TestFieldCache method testDocValuesIntegration.

public void testDocValuesIntegration() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = newIndexWriterConfig(null);
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);
    Document doc = new Document();
    doc.add(new BinaryDocValuesField("binary", new BytesRef("binary value")));
    doc.add(new SortedDocValuesField("sorted", new BytesRef("sorted value")));
    doc.add(new NumericDocValuesField("numeric", 42));
    doc.add(new SortedSetDocValuesField("sortedset", new BytesRef("sortedset value1")));
    doc.add(new SortedSetDocValuesField("sortedset", new BytesRef("sortedset value2")));
    iw.addDocument(doc);
    DirectoryReader ir = iw.getReader();
    iw.close();
    LeafReader ar = getOnlyLeafReader(ir);
    // Binary type: can be retrieved via getTerms()
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getNumerics(ar, "binary", FieldCache.INT_POINT_PARSER);
    });
    BinaryDocValues binary = FieldCache.DEFAULT.getTerms(ar, "binary");
    assertEquals(0, binary.nextDoc());
    final BytesRef term = binary.binaryValue();
    assertEquals("binary value", term.utf8ToString());
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getTermsIndex(ar, "binary");
    });
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getDocTermOrds(ar, "binary", null);
    });
    expectThrows(IllegalStateException.class, () -> {
        new DocTermOrds(ar, null, "binary");
    });
    Bits bits = FieldCache.DEFAULT.getDocsWithField(ar, "binary", null);
    assertTrue(bits.get(0));
    // Sorted type: can be retrieved via getTerms(), getTermsIndex(), getDocTermOrds()
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getNumerics(ar, "sorted", FieldCache.INT_POINT_PARSER);
    });
    expectThrows(IllegalStateException.class, () -> {
        new DocTermOrds(ar, null, "sorted");
    });
    binary = FieldCache.DEFAULT.getTerms(ar, "sorted");
    assertEquals(0, binary.nextDoc());
    BytesRef scratch = binary.binaryValue();
    assertEquals("sorted value", scratch.utf8ToString());
    SortedDocValues sorted = FieldCache.DEFAULT.getTermsIndex(ar, "sorted");
    assertEquals(0, sorted.nextDoc());
    assertEquals(0, sorted.ordValue());
    assertEquals(1, sorted.getValueCount());
    scratch = sorted.binaryValue();
    assertEquals("sorted value", scratch.utf8ToString());
    SortedSetDocValues sortedSet = FieldCache.DEFAULT.getDocTermOrds(ar, "sorted", null);
    assertEquals(0, sortedSet.nextDoc());
    assertEquals(0, sortedSet.nextOrd());
    assertEquals(SortedSetDocValues.NO_MORE_ORDS, sortedSet.nextOrd());
    assertEquals(1, sortedSet.getValueCount());
    bits = FieldCache.DEFAULT.getDocsWithField(ar, "sorted", null);
    assertTrue(bits.get(0));
    // Numeric type: can be retrieved via getInts() and so on
    NumericDocValues numeric = FieldCache.DEFAULT.getNumerics(ar, "numeric", FieldCache.INT_POINT_PARSER);
    assertEquals(0, numeric.nextDoc());
    assertEquals(42, numeric.longValue());
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getTerms(ar, "numeric");
    });
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getTermsIndex(ar, "numeric");
    });
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getDocTermOrds(ar, "numeric", null);
    });
    expectThrows(IllegalStateException.class, () -> {
        new DocTermOrds(ar, null, "numeric");
    });
    bits = FieldCache.DEFAULT.getDocsWithField(ar, "numeric", null);
    assertTrue(bits.get(0));
    // SortedSet type: can be retrieved via getDocTermOrds() 
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getNumerics(ar, "sortedset", FieldCache.INT_POINT_PARSER);
    });
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getTerms(ar, "sortedset");
    });
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getTermsIndex(ar, "sortedset");
    });
    expectThrows(IllegalStateException.class, () -> {
        new DocTermOrds(ar, null, "sortedset");
    });
    sortedSet = FieldCache.DEFAULT.getDocTermOrds(ar, "sortedset", null);
    assertEquals(0, sortedSet.nextDoc());
    assertEquals(0, sortedSet.nextOrd());
    assertEquals(1, sortedSet.nextOrd());
    assertEquals(SortedSetDocValues.NO_MORE_ORDS, sortedSet.nextOrd());
    assertEquals(2, sortedSet.getValueCount());
    bits = FieldCache.DEFAULT.getDocsWithField(ar, "sortedset", null);
    assertTrue(bits.get(0));
    ir.close();
    dir.close();
}