Search in sources :

Example 11 with ScanSchemaOrchestrator

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

the class TestScanOrchestratorEarlySchema method testColumnReordering.

/**
 * Verify that different table column orders are projected into the
 * SELECT order, preserving vectors, so no schema change for column
 * reordering.
 */
@Test
public void testColumnReordering() {
    ScanOrchestratorBuilder builder = new MockScanBuilder();
    builder.enableSchemaSmoothing(true);
    builder.projection(RowSetTestUtils.projectList("a", "b", "c"));
    ScanSchemaOrchestrator scanner = new ScanSchemaOrchestrator(fixture.allocator(), builder);
    TupleMetadata schema1 = new SchemaBuilder().add("a", MinorType.INT).addNullable("b", MinorType.VARCHAR, 10).add("c", MinorType.BIGINT).buildSchema();
    TupleMetadata schema2 = new SchemaBuilder().add("c", MinorType.BIGINT).add("a", MinorType.INT).addNullable("b", MinorType.VARCHAR, 10).buildSchema();
    TupleMetadata schema3 = new SchemaBuilder().add("a", MinorType.INT).add("c", MinorType.BIGINT).addNullable("b", MinorType.VARCHAR, 10).buildSchema();
    SchemaTracker tracker = new SchemaTracker();
    int schemaVersion;
    {
        // ... FROM table 1
        ReaderSchemaOrchestrator reader = scanner.startReader();
        // Projection of (a, b, c) to (a, b, c)
        ResultSetLoader loader = reader.makeTableLoader(schema1);
        reader.startBatch();
        loader.writer().addRow(10, "fred", 110L).addRow(20, "wilma", 110L);
        reader.endBatch();
        tracker.trackSchema(scanner.output());
        schemaVersion = tracker.schemaVersion();
        SingleRowSet expected = fixture.rowSetBuilder(schema1).addRow(10, "fred", 110L).addRow(20, "wilma", 110L).build();
        RowSetUtilities.verify(expected, fixture.wrap(scanner.output()));
        scanner.closeReader();
    }
    {
        // ... FROM table 2
        ReaderSchemaOrchestrator reader = scanner.startReader();
        // Projection of (c, a, b) to (a, b, c)
        ResultSetLoader loader = reader.makeTableLoader(schema2);
        reader.startBatch();
        loader.writer().addRow(330L, 30, "bambam").addRow(440L, 40, "betty");
        reader.endBatch();
        tracker.trackSchema(scanner.output());
        assertEquals(schemaVersion, tracker.schemaVersion());
        SingleRowSet expected = fixture.rowSetBuilder(schema1).addRow(30, "bambam", 330L).addRow(40, "betty", 440L).build();
        RowSetUtilities.verify(expected, fixture.wrap(scanner.output()));
    }
    {
        // ... FROM table 3
        ReaderSchemaOrchestrator reader = scanner.startReader();
        // Projection of (a, c, b) to (a, b, c)
        ResultSetLoader loader = reader.makeTableLoader(schema3);
        reader.startBatch();
        loader.writer().addRow(50, 550L, "dino").addRow(60, 660L, "barney");
        reader.endBatch();
        tracker.trackSchema(scanner.output());
        assertEquals(schemaVersion, tracker.schemaVersion());
        SingleRowSet expected = fixture.rowSetBuilder(schema1).addRow(50, "dino", 550L).addRow(60, "barney", 660L).build();
        RowSetUtilities.verify(expected, fixture.wrap(scanner.output()));
    }
    scanner.close();
}
Also used : SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) ResultSetLoader(org.apache.drill.exec.physical.resultSet.ResultSetLoader) ScanOrchestratorBuilder(org.apache.drill.exec.physical.impl.scan.project.ScanSchemaOrchestrator.ScanOrchestratorBuilder) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) BatchSchemaBuilder(org.apache.drill.exec.record.BatchSchemaBuilder) SchemaTracker(org.apache.drill.exec.physical.impl.protocol.SchemaTracker) MockScanBuilder(org.apache.drill.exec.physical.impl.scan.ScanTestUtils.MockScanBuilder) ScanSchemaOrchestrator(org.apache.drill.exec.physical.impl.scan.project.ScanSchemaOrchestrator) ReaderSchemaOrchestrator(org.apache.drill.exec.physical.impl.scan.project.ReaderSchemaOrchestrator) SubOperatorTest(org.apache.drill.test.SubOperatorTest) Test(org.junit.Test)

Example 12 with ScanSchemaOrchestrator

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

the class TestScanOrchestratorEarlySchema method testEarlySchemaSelectAllReorder.

/**
 * Test SELECT b, a FROM table(a, b)
 */
@Test
public void testEarlySchemaSelectAllReorder() {
    ScanOrchestratorBuilder builder = new MockScanBuilder();
    // SELECT b, a ...
    builder.projection(RowSetTestUtils.projectList("b", "a"));
    ScanSchemaOrchestrator scanner = new ScanSchemaOrchestrator(fixture.allocator(), builder);
    // ... FROM table
    ReaderSchemaOrchestrator reader = scanner.startReader();
    // file schema (a, b)
    TupleMetadata tableSchema = new SchemaBuilder().add("a", MinorType.INT).add("b", MinorType.VARCHAR).buildSchema();
    // Create the table loader
    ResultSetLoader loader = reader.makeTableLoader(tableSchema);
    TupleMetadata expectedSchema = new SchemaBuilder().add("b", MinorType.VARCHAR).add("a", MinorType.INT).buildSchema();
    // Create a batch of data.
    reader.startBatch();
    loader.writer().addRow(1, "fred").addRow(2, "wilma");
    reader.endBatch();
    // Verify
    SingleRowSet expected = fixture.rowSetBuilder(expectedSchema).addRow("fred", 1).addRow("wilma", 2).build();
    RowSetUtilities.verify(expected, fixture.wrap(scanner.output()));
    scanner.close();
}
Also used : SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) ResultSetLoader(org.apache.drill.exec.physical.resultSet.ResultSetLoader) ScanOrchestratorBuilder(org.apache.drill.exec.physical.impl.scan.project.ScanSchemaOrchestrator.ScanOrchestratorBuilder) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) BatchSchemaBuilder(org.apache.drill.exec.record.BatchSchemaBuilder) MockScanBuilder(org.apache.drill.exec.physical.impl.scan.ScanTestUtils.MockScanBuilder) ScanSchemaOrchestrator(org.apache.drill.exec.physical.impl.scan.project.ScanSchemaOrchestrator) ReaderSchemaOrchestrator(org.apache.drill.exec.physical.impl.scan.project.ReaderSchemaOrchestrator) SubOperatorTest(org.apache.drill.test.SubOperatorTest) Test(org.junit.Test)

Example 13 with ScanSchemaOrchestrator

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

the class TestScanOrchestratorEarlySchema method testEmptySchemaExtra.

/**
 * Test SELECT a from an early-schema table of () (that is,
 * a schema that consists of zero columns.
 */
@Test
public void testEmptySchemaExtra() {
    ScanOrchestratorBuilder builder = new MockScanBuilder();
    // SELECT * ...
    builder.projection(RowSetTestUtils.projectList("a"));
    ScanSchemaOrchestrator scanner = new ScanSchemaOrchestrator(fixture.allocator(), builder);
    // ... FROM table
    ReaderSchemaOrchestrator reader = scanner.startReader();
    // file schema ()
    TupleMetadata tableSchema = new SchemaBuilder().buildSchema();
    // Create the table loader
    reader.makeTableLoader(tableSchema);
    TupleMetadata expectedSchema = new SchemaBuilder().addNullable("a", MinorType.INT).buildSchema();
    // Create a batch of data. Because there are no columns, it does
    // not make sense to ready any rows.
    reader.startBatch();
    reader.endBatch();
    // Verify
    SingleRowSet expected = fixture.rowSetBuilder(expectedSchema).build();
    RowSetUtilities.verify(expected, fixture.wrap(scanner.output()));
    scanner.close();
}
Also used : SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) ScanOrchestratorBuilder(org.apache.drill.exec.physical.impl.scan.project.ScanSchemaOrchestrator.ScanOrchestratorBuilder) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) BatchSchemaBuilder(org.apache.drill.exec.record.BatchSchemaBuilder) MockScanBuilder(org.apache.drill.exec.physical.impl.scan.ScanTestUtils.MockScanBuilder) ScanSchemaOrchestrator(org.apache.drill.exec.physical.impl.scan.project.ScanSchemaOrchestrator) ReaderSchemaOrchestrator(org.apache.drill.exec.physical.impl.scan.project.ReaderSchemaOrchestrator) SubOperatorTest(org.apache.drill.test.SubOperatorTest) Test(org.junit.Test)

Example 14 with ScanSchemaOrchestrator

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

the class TestScanOrchestratorEarlySchema method testEarlySchemaSelectExtraCustomType.

/**
 * Test SELECT a, b, c FROM table(a, b)
 * c will be null of type VARCHAR
 */
@Test
public void testEarlySchemaSelectExtraCustomType() {
    ScanOrchestratorBuilder builder = new MockScanBuilder();
    // Null columns of type VARCHAR
    MajorType nullType = MajorType.newBuilder().setMinorType(MinorType.VARCHAR).setMode(DataMode.OPTIONAL).build();
    builder.nullType(nullType);
    // SELECT a, b, c ...
    builder.projection(RowSetTestUtils.projectList("a", "b", "c"));
    ScanSchemaOrchestrator scanner = new ScanSchemaOrchestrator(fixture.allocator(), builder);
    // ... FROM table ...
    ReaderSchemaOrchestrator reader = scanner.startReader();
    // file schema (a, b)
    TupleMetadata tableSchema = new SchemaBuilder().add("a", MinorType.INT).add("b", MinorType.VARCHAR).buildSchema();
    // Create the table loader
    ResultSetLoader loader = reader.makeTableLoader(tableSchema);
    TupleMetadata expectedSchema = new SchemaBuilder().add("a", MinorType.INT).add("b", MinorType.VARCHAR).addNullable("c", MinorType.VARCHAR).buildSchema();
    // Create a batch of data.
    reader.startBatch();
    loader.writer().addRow(1, "fred").addRow(2, "wilma");
    reader.endBatch();
    // Verify
    SingleRowSet expected = fixture.rowSetBuilder(expectedSchema).addRow(1, "fred", null).addRow(2, "wilma", null).build();
    RowSetUtilities.verify(expected, fixture.wrap(scanner.output()));
    scanner.close();
}
Also used : SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) ResultSetLoader(org.apache.drill.exec.physical.resultSet.ResultSetLoader) ScanOrchestratorBuilder(org.apache.drill.exec.physical.impl.scan.project.ScanSchemaOrchestrator.ScanOrchestratorBuilder) MajorType(org.apache.drill.common.types.TypeProtos.MajorType) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) BatchSchemaBuilder(org.apache.drill.exec.record.BatchSchemaBuilder) MockScanBuilder(org.apache.drill.exec.physical.impl.scan.ScanTestUtils.MockScanBuilder) ScanSchemaOrchestrator(org.apache.drill.exec.physical.impl.scan.project.ScanSchemaOrchestrator) ReaderSchemaOrchestrator(org.apache.drill.exec.physical.impl.scan.project.ReaderSchemaOrchestrator) SubOperatorTest(org.apache.drill.test.SubOperatorTest) Test(org.junit.Test)

Example 15 with ScanSchemaOrchestrator

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

the class TestScanOrchestratorEarlySchema method testEarlySchemaSelectSubset.

/**
 * Test SELECT a FROM table(a, b)
 */
@Test
public void testEarlySchemaSelectSubset() {
    ScanOrchestratorBuilder builder = new MockScanBuilder();
    // SELECT a ...
    builder.projection(RowSetTestUtils.projectList("a"));
    ScanSchemaOrchestrator scanner = new ScanSchemaOrchestrator(fixture.allocator(), builder);
    // ... FROM table
    ReaderSchemaOrchestrator reader = scanner.startReader();
    // file schema (a, b)
    TupleMetadata tableSchema = new SchemaBuilder().add("a", MinorType.INT).add("b", MinorType.VARCHAR).buildSchema();
    // Create the table loader
    ResultSetLoader loader = reader.makeTableLoader(tableSchema);
    // Verify that unprojected column is unprojected in the
    // table loader.
    assertFalse(loader.writer().column("b").isProjected());
    TupleMetadata expectedSchema = new SchemaBuilder().add("a", MinorType.INT).buildSchema();
    // Create a batch of data.
    reader.startBatch();
    loader.writer().addRow(1, "fred").addRow(2, "wilma");
    reader.endBatch();
    // Verify
    SingleRowSet expected = fixture.rowSetBuilder(expectedSchema).addRow(1).addRow(2).build();
    RowSetUtilities.verify(expected, fixture.wrap(scanner.output()));
    scanner.close();
}
Also used : SingleRowSet(org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet) ResultSetLoader(org.apache.drill.exec.physical.resultSet.ResultSetLoader) ScanOrchestratorBuilder(org.apache.drill.exec.physical.impl.scan.project.ScanSchemaOrchestrator.ScanOrchestratorBuilder) TupleMetadata(org.apache.drill.exec.record.metadata.TupleMetadata) SchemaBuilder(org.apache.drill.exec.record.metadata.SchemaBuilder) BatchSchemaBuilder(org.apache.drill.exec.record.BatchSchemaBuilder) MockScanBuilder(org.apache.drill.exec.physical.impl.scan.ScanTestUtils.MockScanBuilder) ScanSchemaOrchestrator(org.apache.drill.exec.physical.impl.scan.project.ScanSchemaOrchestrator) ReaderSchemaOrchestrator(org.apache.drill.exec.physical.impl.scan.project.ReaderSchemaOrchestrator) SubOperatorTest(org.apache.drill.test.SubOperatorTest) Test(org.junit.Test)

Aggregations

ScanSchemaOrchestrator (org.apache.drill.exec.physical.impl.scan.project.ScanSchemaOrchestrator)26 SchemaBuilder (org.apache.drill.exec.record.metadata.SchemaBuilder)24 TupleMetadata (org.apache.drill.exec.record.metadata.TupleMetadata)24 ReaderSchemaOrchestrator (org.apache.drill.exec.physical.impl.scan.project.ReaderSchemaOrchestrator)23 SubOperatorTest (org.apache.drill.test.SubOperatorTest)23 Test (org.junit.Test)23 ScanOrchestratorBuilder (org.apache.drill.exec.physical.impl.scan.project.ScanSchemaOrchestrator.ScanOrchestratorBuilder)22 MockScanBuilder (org.apache.drill.exec.physical.impl.scan.ScanTestUtils.MockScanBuilder)21 SingleRowSet (org.apache.drill.exec.physical.rowSet.RowSet.SingleRowSet)20 ResultSetLoader (org.apache.drill.exec.physical.resultSet.ResultSetLoader)18 BatchSchemaBuilder (org.apache.drill.exec.record.BatchSchemaBuilder)13 SchemaPath (org.apache.drill.common.expression.SchemaPath)6 ImplicitColumnManager (org.apache.drill.exec.physical.impl.scan.file.ImplicitColumnManager)6 Path (org.apache.hadoop.fs.Path)6 File (java.io.File)5 SchemaTracker (org.apache.drill.exec.physical.impl.protocol.SchemaTracker)5 MajorType (org.apache.drill.common.types.TypeProtos.MajorType)2 ColumnsArrayManager (org.apache.drill.exec.physical.impl.scan.columns.ColumnsArrayManager)2 RowSetLoader (org.apache.drill.exec.physical.resultSet.RowSetLoader)2 BatchSchema (org.apache.drill.exec.record.BatchSchema)2