Search in sources :

Example 21 with RowBatchReader

use of org.apache.drill.exec.physical.impl.scan.RowBatchReader in project drill by apache.

the class TestFileScanLifecycle method testPartitionColumnTwoDigits.

/**
 * Test the obscure case that the partition column contains two digits:
 * dir11. Also tests the obscure case that the output only has partition
 * columns.
 */
@Test
public void testPartitionColumnTwoDigits() {
    Path filePath = new Path("file:/w/0/1/2/3/4/5/6/7/8/9/10/d11/z.csv");
    FileScanLifecycleBuilder builder = new FileScanLifecycleBuilder();
    builder.rootDir(MOCK_ROOT_PATH);
    builder.maxPartitionDepth(11);
    builder.projection(RowSetTestUtils.projectList("a", "b", FileScanUtils.partitionColName(11)));
    builder.fileSplits(Collections.singletonList(new DummyFileWork(filePath)));
    builder.useLegacyWildcardExpansion(true);
    builder.readerFactory(new FileReaderFactory() {

        @Override
        public ManagedReader newReader(FileSchemaNegotiator negotiator) {
            return new MockEarlySchemaReader(negotiator, 1);
        }
    });
    ScanLifecycle scan = buildScan(builder);
    RowBatchReader reader = scan.nextReader();
    assertTrue(reader.open());
    assertTrue(reader.next());
    TupleMetadata expectedSchema = new SchemaBuilder().addAll(SCHEMA).add(FileScanUtils.partitionColName(11), PARTITION_COL_TYPE).build();
    RowSet expected = fixture.rowSetBuilder(expectedSchema).addRow(10, "fred", "d11").addRow(20, "wilma", "d11").build();
    RowSetUtilities.verify(expected, fixture.wrap(reader.output()));
    assertFalse(reader.next());
    reader.close();
    scan.close();
}
Also used : SchemaPath(org.apache.drill.common.expression.SchemaPath) Path(org.apache.hadoop.fs.Path) RowBatchReader(org.apache.drill.exec.physical.impl.scan.RowBatchReader) ManagedReader(org.apache.drill.exec.physical.impl.scan.v3.ManagedReader) RowSet(org.apache.drill.exec.physical.rowSet.RowSet) DummyFileWork(org.apache.drill.exec.physical.impl.scan.v3.file.BaseFileScanTest.DummyFileWork) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) ScanLifecycle(org.apache.drill.exec.physical.impl.scan.v3.lifecycle.ScanLifecycle) BaseTestScanLifecycle(org.apache.drill.exec.physical.impl.scan.v3.lifecycle.BaseTestScanLifecycle) Test(org.junit.Test) EvfTest(org.apache.drill.categories.EvfTest)

Example 22 with RowBatchReader

use of org.apache.drill.exec.physical.impl.scan.RowBatchReader in project drill by apache.

the class TestFileScanLifecycle method testAllColumns.

@Test
public void testAllColumns() {
    FileScanLifecycleBuilder builder = new FileScanLifecycleBuilder();
    builder.rootDir(MOCK_ROOT_PATH);
    builder.maxPartitionDepth(3);
    builder.projection(FileScanUtils.projectAllWithMetadata(3));
    builder.fileSplits(Collections.singletonList(new DummyFileWork(MOCK_FILE_PATH)));
    builder.useLegacyWildcardExpansion(true);
    builder.readerFactory(new FileReaderFactory() {

        @Override
        public ManagedReader newReader(FileSchemaNegotiator negotiator) {
            return new MockEarlySchemaReader(negotiator, 1);
        }
    });
    ScanLifecycle scan = buildScan(builder);
    assertSame(ProjectionType.ALL, scan.schemaTracker().projectionType());
    RowBatchReader reader = scan.nextReader();
    assertTrue(reader.open());
    assertTrue(reader.next());
    TupleMetadata expectedSchema = new SchemaBuilder().addAll(SCHEMA).add(FileScanUtils.FULLY_QUALIFIED_NAME_COL, IMPLICIT_COL_TYPE).add(FileScanUtils.FILE_PATH_COL, IMPLICIT_COL_TYPE).add(FileScanUtils.FILE_NAME_COL, IMPLICIT_COL_TYPE).add(FileScanUtils.SUFFIX_COL, IMPLICIT_COL_TYPE).add(FileScanUtils.partitionColName(0), PARTITION_COL_TYPE).add(FileScanUtils.partitionColName(1), PARTITION_COL_TYPE).add(FileScanUtils.partitionColName(2), PARTITION_COL_TYPE).build();
    RowSet expected = fixture.rowSetBuilder(expectedSchema).addRow(10, "fred", MOCK_FILE_FQN, MOCK_FILE_DIR_PATH, MOCK_FILE_NAME, MOCK_SUFFIX, MOCK_DIR0, MOCK_DIR1, null).addRow(20, "wilma", MOCK_FILE_FQN, MOCK_FILE_DIR_PATH, MOCK_FILE_NAME, MOCK_SUFFIX, MOCK_DIR0, MOCK_DIR1, null).build();
    RowSetUtilities.verify(expected, fixture.wrap(reader.output()));
    assertFalse(reader.next());
    reader.close();
    scan.close();
}
Also used : RowBatchReader(org.apache.drill.exec.physical.impl.scan.RowBatchReader) DummyFileWork(org.apache.drill.exec.physical.impl.scan.v3.file.BaseFileScanTest.DummyFileWork) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) ManagedReader(org.apache.drill.exec.physical.impl.scan.v3.ManagedReader) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) RowSet(org.apache.drill.exec.physical.rowSet.RowSet) ScanLifecycle(org.apache.drill.exec.physical.impl.scan.v3.lifecycle.ScanLifecycle) BaseTestScanLifecycle(org.apache.drill.exec.physical.impl.scan.v3.lifecycle.BaseTestScanLifecycle) Test(org.junit.Test) EvfTest(org.apache.drill.categories.EvfTest)

Example 23 with RowBatchReader

use of org.apache.drill.exec.physical.impl.scan.RowBatchReader in project drill by apache.

the class TestScanLifecycleTwoReaders method testColumnReorderingBA.

/**
 * {@code SELECT * FROM} (b,a) then (a, b). The order of the first
 * table drives the order of the results.
 */
@Test
public void testColumnReorderingBA() {
    ScanLifecycleBuilder builder = new ScanLifecycleBuilder();
    builder.readerFactory(new TwoReaderFactory() {

        @Override
        public ManagedReader firstReader(SchemaNegotiator negotiator) {
            return new MockReorderedReader(negotiator);
        }

        @Override
        public ManagedReader secondReader(SchemaNegotiator negotiator) {
            return new MockLateSchemaReader(negotiator, 1);
        }
    });
    ScanLifecycle scan = buildScan(builder);
    RowBatchReader reader = scan.nextReader();
    reader = scan.nextReader();
    assertTrue(reader.open());
    assertTrue(reader.next());
    RowSet expected = fixture.rowSetBuilder(MockReorderedReader.READER_SCHEMA).addRow("barney", 30).addRow("betty", 40).build();
    RowSetUtilities.verify(expected, fixture.wrap(reader.output()));
    assertFalse(reader.next());
    reader.close();
    reader = scan.nextReader();
    reader = scan.nextReader();
    assertTrue(reader.open());
    assertTrue(reader.next());
    expected = fixture.rowSetBuilder(MockReorderedReader.READER_SCHEMA).addRow("fred", 10).addRow("wilma", 20).build();
    RowSetUtilities.verify(expected, fixture.wrap(reader.output()));
    assertFalse(reader.next());
    reader.close();
    scan.close();
}
Also used : RowBatchReader(org.apache.drill.exec.physical.impl.scan.RowBatchReader) ManagedReader(org.apache.drill.exec.physical.impl.scan.v3.ManagedReader) RowSet(org.apache.drill.exec.physical.rowSet.RowSet) SchemaNegotiator(org.apache.drill.exec.physical.impl.scan.v3.SchemaNegotiator) ScanLifecycleBuilder(org.apache.drill.exec.physical.impl.scan.v3.ScanLifecycleBuilder) Test(org.junit.Test) EvfTest(org.apache.drill.categories.EvfTest)

Example 24 with RowBatchReader

use of org.apache.drill.exec.physical.impl.scan.RowBatchReader in project drill by apache.

the class BaseTestScanLifecycle method verifyEmptyReader.

protected void verifyEmptyReader(ScanLifecycle scan) {
    RowBatchReader reader = scan.nextReader();
    assertTrue(reader.open());
    assertFalse(reader.next());
    assertFalse(scan.hasOutputSchema());
    reader.close();
}
Also used : RowBatchReader(org.apache.drill.exec.physical.impl.scan.RowBatchReader)

Example 25 with RowBatchReader

use of org.apache.drill.exec.physical.impl.scan.RowBatchReader in project drill by apache.

the class TestScanLifecycleBasics method testEarlySchemaWithProject.

/**
 * Test SELECT a, c FROM table(a, b)
 */
@Test
public void testEarlySchemaWithProject() {
    ScanLifecycleBuilder builder = new ScanLifecycleBuilder();
    builder.projection(RowSetTestUtils.projectList("a", "c"));
    builder.readerFactory(new SingleReaderFactory() {

        @Override
        public ManagedReader next(SchemaNegotiator negotiator) {
            return new MockEarlySchemaReader(negotiator, 1);
        }
    });
    ScanLifecycle scan = buildScan(builder);
    assertSame(ProjectionType.SOME, scan.schemaTracker().projectionType());
    RowBatchReader reader = scan.nextReader();
    assertTrue(reader.open());
    // Early schema: so output schema is available after open
    TupleMetadata expectedSchema = new SchemaBuilder().add("a", MinorType.INT).addNullable("c", MinorType.INT).build();
    assertEquals(expectedSchema, scan.outputSchema());
    assertTrue(reader.next());
    RowSet expected = fixture.rowSetBuilder(expectedSchema).addRow(10, null).addRow(20, null).build();
    RowSetUtilities.verify(expected, fixture.wrap(reader.output()));
    assertFalse(reader.next());
    reader.close();
    scan.close();
}
Also used : RowBatchReader(org.apache.drill.exec.physical.impl.scan.RowBatchReader) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) ManagedReader(org.apache.drill.exec.physical.impl.scan.v3.ManagedReader) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) RowSet(org.apache.drill.exec.physical.rowSet.RowSet) SchemaNegotiator(org.apache.drill.exec.physical.impl.scan.v3.SchemaNegotiator) ScanLifecycleBuilder(org.apache.drill.exec.physical.impl.scan.v3.ScanLifecycleBuilder) Test(org.junit.Test) EvfTest(org.apache.drill.categories.EvfTest)

Aggregations

RowBatchReader (org.apache.drill.exec.physical.impl.scan.RowBatchReader)51 Test (org.junit.Test)48 ManagedReader (org.apache.drill.exec.physical.impl.scan.v3.ManagedReader)43 EvfTest (org.apache.drill.categories.EvfTest)42 ScanLifecycleBuilder (org.apache.drill.exec.physical.impl.scan.v3.ScanLifecycleBuilder)37 SchemaNegotiator (org.apache.drill.exec.physical.impl.scan.v3.SchemaNegotiator)37 RowSet (org.apache.drill.exec.physical.rowSet.RowSet)28 SchemaBuilder (org.apache.drill.exec.record.metadata.SchemaBuilder)13 TupleMetadata (org.apache.drill.exec.record.metadata.TupleMetadata)13 UserException (org.apache.drill.common.exceptions.UserException)12 DummyFileWork (org.apache.drill.exec.physical.impl.scan.v3.file.BaseFileScanTest.DummyFileWork)6 BaseTestScanLifecycle (org.apache.drill.exec.physical.impl.scan.v3.lifecycle.BaseTestScanLifecycle)6 ScanLifecycle (org.apache.drill.exec.physical.impl.scan.v3.lifecycle.ScanLifecycle)6 SchemaPath (org.apache.drill.common.expression.SchemaPath)1 EarlyEofException (org.apache.drill.exec.physical.impl.scan.v3.ManagedReader.EarlyEofException)1 VectorContainer (org.apache.drill.exec.record.VectorContainer)1 Path (org.apache.hadoop.fs.Path)1