Search in sources :

Example 11 with DictWriter

use of org.apache.drill.exec.vector.accessor.DictWriter in project drill by apache.

the class TestResultSetLoaderDicts method testMapValueNullableFields.

/**
 * Create dict with map value. Then, add columns to the map
 * on the fly. Use required, variable-width columns since
 * those require the most processing and are most likely to
 * fail if anything is out of place.
 */
@Test
public void testMapValueNullableFields() {
    final TupleMetadata schema = new SchemaBuilder().add("a", MinorType.INT).addDict("d", MinorType.VARCHAR).mapValue().addNullable("b", MinorType.VARCHAR).resumeDict().resumeSchema().buildSchema();
    final ResultSetLoaderImpl.ResultSetOptions options = new ResultSetOptionBuilder().readerSchema(schema).build();
    final ResultSetLoader rsLoader = new ResultSetLoaderImpl(fixture.allocator(), options);
    assertEquals(5, rsLoader.schemaVersion());
    final RowSetLoader rootWriter = rsLoader.writer();
    rsLoader.startBatch();
    rootWriter.addRow(10, map("a", mapValue("c1"), "b", mapValue("c2")));
    // Validate first batch
    RowSet actual = fixture.wrap(rsLoader.harvest());
    assertEquals(5, rsLoader.schemaVersion());
    SingleRowSet expected = fixture.rowSetBuilder(schema).addRow(10, map("a", mapValue("c1"), "b", mapValue("c2"))).build();
    RowSetUtilities.verify(expected, actual);
    // Now add columns in the second batch.
    rsLoader.startBatch();
    rootWriter.addRow(20, map("a2", mapValue("c11"), "b2", mapValue("c12"), "c2", mapValue("c13")));
    final DictWriter dictWriter = rootWriter.dict("d");
    final TupleWriter nestedMapWriter = dictWriter.valueWriter().tuple();
    nestedMapWriter.addColumn(SchemaBuilder.columnSchema("c", MinorType.VARCHAR, DataMode.OPTIONAL));
    rootWriter.addRow(30, map("a3", mapValue("c21", "d21")));
    // And another set while the write proceeds.
    nestedMapWriter.addColumn(SchemaBuilder.columnSchema("d", MinorType.VARCHAR, DataMode.OPTIONAL));
    rootWriter.addRow(40, map("a4", mapValue("c31", "d31", "e31"), "b4", mapValue("c32", "d32", "e32")));
    // Validate second batch
    actual = fixture.wrap(rsLoader.harvest());
    assertEquals(7, rsLoader.schemaVersion());
    final TupleMetadata expectedSchema = new SchemaBuilder().add("a", MinorType.INT).addDict("d", MinorType.VARCHAR).mapValue().addNullable("b", MinorType.VARCHAR).addNullable("c", MinorType.VARCHAR).addNullable("d", MinorType.VARCHAR).resumeDict().resumeSchema().buildSchema();
    expected = fixture.rowSetBuilder(expectedSchema).addRow(20, map("a2", mapValue("c11", null, null), "b2", mapValue("c12", null, null), "c2", mapValue("c13", null, null))).addRow(30, map("a3", mapValue("c21", "d21", null))).addRow(40, map("a4", mapValue("c31", "d31", "e31"), "b4", mapValue("c32", "d32", "e32"))).build();
    RowSetUtilities.verify(expected, actual);
    rsLoader.close();
}
Also used : DictWriter(org.apache.drill.exec.vector.accessor.DictWriter) SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) ResultSetLoader(org.apache.drill.exec.physical.resultSet.ResultSetLoader) TupleWriter(org.apache.drill.exec.vector.accessor.TupleWriter) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) RowSet(org.apache.drill.exec.physical.rowSet.RowSet) RowSetLoader(org.apache.drill.exec.physical.resultSet.RowSetLoader) SubOperatorTest(org.apache.drill.test.SubOperatorTest) Test(org.junit.Test)

Example 12 with DictWriter

use of org.apache.drill.exec.vector.accessor.DictWriter in project drill by apache.

the class TestResultSetLoaderDicts method testValueOverflow.

@Test
public void testValueOverflow() {
    TupleMetadata schema = new SchemaBuilder().addDict("d", MinorType.INT).value(MinorType.VARCHAR).resumeSchema().buildSchema();
    ResultSetLoaderImpl.ResultSetOptions options = new ResultSetOptionBuilder().rowCountLimit(ValueVector.MAX_ROW_COUNT).readerSchema(schema).build();
    ResultSetLoader rsLoader = new ResultSetLoaderImpl(fixture.allocator(), options);
    RowSetLoader rootWriter = rsLoader.writer();
    rsLoader.startBatch();
    byte[] value = new byte[523];
    Arrays.fill(value, (byte) 'X');
    // number of entries in each dict
    int dictSize = 4;
    // Number of rows should be driven by vector size.
    // Our row count should include the overflow row
    DictWriter dictWriter = rootWriter.dict(0);
    ScalarWriter keyWriter = dictWriter.keyWriter();
    ScalarWriter valueWriter = dictWriter.valueWriter().scalar();
    int expectedCount = ValueVector.MAX_BUFFER_SIZE / (value.length * dictSize);
    {
        int count = 0;
        while (!rootWriter.isFull()) {
            rootWriter.start();
            for (int i = 0; i < dictSize; i++) {
                // acts as a placeholder, the actual value is not important
                keyWriter.setInt(0);
                valueWriter.setBytes(value, value.length);
                // not necessary for scalars, just for completeness
                dictWriter.save();
            }
            rootWriter.save();
            count++;
        }
        assertEquals(expectedCount + 1, count);
        // Loader's row count should include only "visible" rows
        assertEquals(expectedCount, rootWriter.rowCount());
        // Total count should include invisible and look-ahead rows.
        assertEquals(expectedCount + 1, rsLoader.totalRowCount());
        // Result should exclude the overflow row
        VectorContainer container = rsLoader.harvest();
        BatchValidator.validate(container);
        RowSet result = fixture.wrap(container);
        assertEquals(expectedCount, result.rowCount());
        result.clear();
    }
    // Next batch should start with the overflow row
    {
        rsLoader.startBatch();
        assertEquals(1, rootWriter.rowCount());
        assertEquals(expectedCount + 1, rsLoader.totalRowCount());
        VectorContainer container = rsLoader.harvest();
        BatchValidator.validate(container);
        RowSet result = fixture.wrap(container);
        assertEquals(1, result.rowCount());
        result.clear();
    }
    rsLoader.close();
}
Also used : DictWriter(org.apache.drill.exec.vector.accessor.DictWriter) SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) RowSet(org.apache.drill.exec.physical.rowSet.RowSet) VectorContainer(org.apache.drill.exec.record.VectorContainer) ResultSetLoader(org.apache.drill.exec.physical.resultSet.ResultSetLoader) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) RowSetLoader(org.apache.drill.exec.physical.resultSet.RowSetLoader) ScalarWriter(org.apache.drill.exec.vector.accessor.ScalarWriter) SubOperatorTest(org.apache.drill.test.SubOperatorTest) Test(org.junit.Test)

Example 13 with DictWriter

use of org.apache.drill.exec.vector.accessor.DictWriter in project drill by apache.

the class TestResultSetLoaderDicts method testBasics.

@Test
public void testBasics() {
    final TupleMetadata schema = new SchemaBuilder().add("a", MinorType.INT).addDict("d", MinorType.INT).value(MinorType.VARCHAR).resumeSchema().buildSchema();
    final ResultSetLoaderImpl.ResultSetOptions options = new ResultSetOptionBuilder().readerSchema(schema).build();
    final ResultSetLoader rsLoader = new ResultSetLoaderImpl(fixture.allocator(), options);
    assertFalse(rsLoader.isProjectionEmpty());
    final RowSetLoader rootWriter = rsLoader.writer();
    // Verify structure and schema
    assertEquals(4, rsLoader.schemaVersion());
    final TupleMetadata actualSchema = rootWriter.tupleSchema();
    assertEquals(2, actualSchema.size());
    assertTrue(actualSchema.metadata(1).isDict());
    assertEquals(2, actualSchema.metadata("d").tupleSchema().size());
    assertEquals(2, actualSchema.column("d").getChildren().size());
    rsLoader.startBatch();
    // Write a row the way that clients will do.
    final ScalarWriter aWriter = rootWriter.scalar("a");
    final DictWriter dictWriter = rootWriter.dict("d");
    final ScalarWriter keyWriter = dictWriter.keyWriter();
    final ScalarWriter valueWriter = dictWriter.valueWriter().scalar();
    rootWriter.start();
    aWriter.setInt(10);
    keyWriter.setInt(110);
    valueWriter.setString("fred");
    dictWriter.save();
    keyWriter.setInt(111);
    valueWriter.setString("george");
    dictWriter.save();
    rootWriter.save();
    // Write another using the test-time conveniences
    rootWriter.addRow(20, map(210, "barney", 211, "bart", 212, "jerry"));
    // Harvest the batch
    final RowSet actual = fixture.wrap(rsLoader.harvest());
    assertEquals(4, rsLoader.schemaVersion());
    assertEquals(2, actual.rowCount());
    final DictVector dictVector = (DictVector) actual.container().getValueVector(1).getValueVector();
    assertEquals(2, dictVector.getAccessor().getValueCount());
    // Validate data
    final SingleRowSet expected = fixture.rowSetBuilder(schema).addRow(10, map(110, "fred", 111, "george")).addRow(20, map(210, "barney", 211, "bart", 212, "jerry")).build();
    RowSetUtilities.verify(expected, actual);
    rsLoader.close();
}
Also used : DictVector(org.apache.drill.exec.vector.complex.DictVector) DictWriter(org.apache.drill.exec.vector.accessor.DictWriter) SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) ResultSetLoader(org.apache.drill.exec.physical.resultSet.ResultSetLoader) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) RowSet(org.apache.drill.exec.physical.rowSet.RowSet) RowSetLoader(org.apache.drill.exec.physical.resultSet.RowSetLoader) ScalarWriter(org.apache.drill.exec.vector.accessor.ScalarWriter) SubOperatorTest(org.apache.drill.test.SubOperatorTest) Test(org.junit.Test)

Example 14 with DictWriter

use of org.apache.drill.exec.vector.accessor.DictWriter in project drill by apache.

the class TestResultSetLoaderDicts method testDictAddition.

/**
 * Test adding a dict to a loader after writing the first row.
 */
@Test
public void testDictAddition() {
    final TupleMetadata schema = new SchemaBuilder().add("a", MinorType.INT).buildSchema();
    final ResultSetLoaderImpl.ResultSetOptions options = new ResultSetOptionBuilder().readerSchema(schema).build();
    final ResultSetLoader rsLoader = new ResultSetLoaderImpl(fixture.allocator(), options);
    assertEquals(1, rsLoader.schemaVersion());
    final RowSetLoader rootWriter = rsLoader.writer();
    // Start without the dict. Add then add a dict after the first row.
    rsLoader.startBatch();
    rootWriter.addRow(10);
    MaterializedField dictField = SchemaBuilder.columnSchema("d", MinorType.DICT, DataMode.REQUIRED);
    dictField.addChild(SchemaBuilder.columnSchema(DictVector.FIELD_KEY_NAME, MinorType.VARCHAR, DataMode.REQUIRED));
    dictField.addChild(SchemaBuilder.columnSchema(DictVector.FIELD_VALUE_NAME, MinorType.VARCHAR, DataMode.REQUIRED));
    DictColumnMetadata dictMetadata = MetadataUtils.newDict(dictField);
    final int dictIndex = rootWriter.addColumn(dictMetadata);
    final DictWriter dictWriter = rootWriter.dict(dictIndex);
    // Ensure metadata was added
    final TupleMetadata actualSchema = rootWriter.tupleSchema();
    assertTrue(actualSchema.metadata(1).isDict());
    assertEquals(2, actualSchema.metadata("d").tupleSchema().size());
    assertEquals(2, actualSchema.column("d").getChildren().size());
    assertEquals(2, actualSchema.size());
    assertEquals(2, dictWriter.schema().tupleSchema().size());
    rootWriter.addRow(20, map("name", "fred", "lastname", "smith")).addRow(30, map("name", "barney", "lastname", "johnson"));
    final RowSet actual = fixture.wrap(rsLoader.harvest());
    assertEquals(4, rsLoader.schemaVersion());
    assertEquals(3, actual.rowCount());
    final DictVector dictVector = (DictVector) actual.container().getValueVector(1).getValueVector();
    assertEquals(2, dictVector.getField().getChildren().size());
    // Validate first batch
    final TupleMetadata expectedSchema = new SchemaBuilder().add("a", MinorType.INT).addDict("d", MinorType.VARCHAR).value(MinorType.VARCHAR).resumeSchema().buildSchema();
    final SingleRowSet expected = fixture.rowSetBuilder(expectedSchema).addRow(10, map()).addRow(20, map("name", "fred", "lastname", "smith")).addRow(30, map("name", "barney", "lastname", "johnson")).build();
    RowSetUtilities.verify(expected, actual);
    rsLoader.close();
}
Also used : DictVector(org.apache.drill.exec.vector.complex.DictVector) DictWriter(org.apache.drill.exec.vector.accessor.DictWriter) SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) RowSet(org.apache.drill.exec.physical.rowSet.RowSet) MaterializedField(org.apache.drill.exec.record.MaterializedField) ResultSetLoader(org.apache.drill.exec.physical.resultSet.ResultSetLoader) DictColumnMetadata(org.apache.drill.exec.record.metadata.DictColumnMetadata) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) RowSetLoader(org.apache.drill.exec.physical.resultSet.RowSetLoader) SubOperatorTest(org.apache.drill.test.SubOperatorTest) Test(org.junit.Test)

Example 15 with DictWriter

use of org.apache.drill.exec.vector.accessor.DictWriter in project drill by apache.

the class TestResultSetLoaderDicts method testMapValueRequiredFields.

/**
 * Create dict with map value. Then, add columns to the map
 * on the fly. Use required, variable-width columns since
 * those require the most processing and are most likely to
 * fail if anything is out of place.
 */
@Test
public void testMapValueRequiredFields() {
    final TupleMetadata schema = new SchemaBuilder().add("a", MinorType.INT).addDict("d", MinorType.VARCHAR).mapValue().add("b", MinorType.VARCHAR).resumeDict().resumeSchema().buildSchema();
    final ResultSetLoaderImpl.ResultSetOptions options = new ResultSetOptionBuilder().readerSchema(schema).build();
    final ResultSetLoader rsLoader = new ResultSetLoaderImpl(fixture.allocator(), options);
    assertEquals(5, rsLoader.schemaVersion());
    final RowSetLoader rootWriter = rsLoader.writer();
    rsLoader.startBatch();
    rootWriter.addRow(10, map("a", mapValue("c1"), "b", mapValue("c2")));
    // Validate first batch
    RowSet actual = fixture.wrap(rsLoader.harvest());
    assertEquals(5, rsLoader.schemaVersion());
    SingleRowSet expected = fixture.rowSetBuilder(schema).addRow(10, map("a", mapValue("c1"), "b", mapValue("c2"))).build();
    RowSetUtilities.verify(expected, actual);
    // Now add columns in the second batch.
    rsLoader.startBatch();
    rootWriter.addRow(20, map("a2", mapValue("c11"), "b2", mapValue("c12"), "c2", mapValue("c13")));
    final DictWriter dictWriter = rootWriter.dict("d");
    final TupleWriter nestedMapWriter = dictWriter.valueWriter().tuple();
    nestedMapWriter.addColumn(SchemaBuilder.columnSchema("c", MinorType.VARCHAR, DataMode.REQUIRED));
    rootWriter.addRow(30, map("a3", mapValue("c21", "d21")));
    // And another set while the write proceeds.
    nestedMapWriter.addColumn(SchemaBuilder.columnSchema("d", MinorType.VARCHAR, DataMode.REQUIRED));
    rootWriter.addRow(40, map("a4", mapValue("c31", "d31", "e31"), "b4", mapValue("c32", "d32", "e32")));
    // Validate second batch
    actual = fixture.wrap(rsLoader.harvest());
    assertEquals(7, rsLoader.schemaVersion());
    final TupleMetadata expectedSchema = new SchemaBuilder().add("a", MinorType.INT).addDict("d", MinorType.VARCHAR).mapValue().add("b", MinorType.VARCHAR).add("c", MinorType.VARCHAR).add("d", MinorType.VARCHAR).resumeDict().resumeSchema().buildSchema();
    expected = fixture.rowSetBuilder(expectedSchema).addRow(20, map("a2", mapValue("c11", "", ""), "b2", mapValue("c12", "", ""), "c2", mapValue("c13", "", ""))).addRow(30, map("a3", mapValue("c21", "d21", ""))).addRow(40, map("a4", mapValue("c31", "d31", "e31"), "b4", mapValue("c32", "d32", "e32"))).build();
    RowSetUtilities.verify(expected, actual);
    rsLoader.close();
}
Also used : DictWriter(org.apache.drill.exec.vector.accessor.DictWriter) SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) ResultSetLoader(org.apache.drill.exec.physical.resultSet.ResultSetLoader) TupleWriter(org.apache.drill.exec.vector.accessor.TupleWriter) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) RowSet(org.apache.drill.exec.physical.rowSet.RowSet) RowSetLoader(org.apache.drill.exec.physical.resultSet.RowSetLoader) SubOperatorTest(org.apache.drill.test.SubOperatorTest) Test(org.junit.Test)

Aggregations

DictWriter (org.apache.drill.exec.vector.accessor.DictWriter)16 SchemaBuilder (org.apache.drill.exec.record.metadata.SchemaBuilder)15 TupleMetadata (org.apache.drill.exec.record.metadata.TupleMetadata)15 SubOperatorTest (org.apache.drill.test.SubOperatorTest)15 Test (org.junit.Test)15 SingleRowSet (org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet)13 ResultSetLoader (org.apache.drill.exec.physical.resultSet.ResultSetLoader)11 RowSetLoader (org.apache.drill.exec.physical.resultSet.RowSetLoader)11 RowSet (org.apache.drill.exec.physical.rowSet.RowSet)9 ScalarWriter (org.apache.drill.exec.vector.accessor.ScalarWriter)8 DictVector (org.apache.drill.exec.vector.complex.DictVector)5 VectorContainer (org.apache.drill.exec.record.VectorContainer)4 ArrayWriter (org.apache.drill.exec.vector.accessor.ArrayWriter)4 RepeatedDictVector (org.apache.drill.exec.vector.complex.RepeatedDictVector)4 ExtendableRowSet (org.apache.drill.exec.physical.rowSet.RowSet.ExtendableRowSet)3 DictReader (org.apache.drill.exec.vector.accessor.DictReader)3 KeyAccessor (org.apache.drill.exec.vector.accessor.KeyAccessor)3 TupleWriter (org.apache.drill.exec.vector.accessor.TupleWriter)3 MaterializedField (org.apache.drill.exec.record.MaterializedField)2 ColumnMetadata (org.apache.drill.exec.record.metadata.ColumnMetadata)2