Search in sources :

Example 66 with SchemaPath

use of org.apache.drill.common.expression.SchemaPath in project drill by apache.

the class TestOrderedPartitionExchange method twoBitTwoExchangeRun.

/**
   * Starts two drillbits and runs a physical plan with a Mock scan, project, OrderedParititionExchange, Union Exchange,
   * and sort. The final sort is done first on the partition column, and verifies that the partitions are correct, in that
   * all rows in partition 0 should come in the sort order before any row in partition 1, etc. Also verifies that the standard
   * deviation of the size of the partitions is less than one tenth the mean size of the partitions, because we expect all
   * the partitions to be roughly equal in size.
   * @throws Exception
   */
@Test
public void twoBitTwoExchangeRun() throws Exception {
    RemoteServiceSet serviceSet = RemoteServiceSet.getLocalServiceSet();
    try (Drillbit bit1 = new Drillbit(CONFIG, serviceSet);
        Drillbit bit2 = new Drillbit(CONFIG, serviceSet);
        DrillClient client = new DrillClient(CONFIG, serviceSet.getCoordinator())) {
        bit1.run();
        bit2.run();
        client.connect();
        List<QueryDataBatch> results = client.runQuery(org.apache.drill.exec.proto.UserBitShared.QueryType.PHYSICAL, Files.toString(FileUtils.getResourceAsFile("/sender/ordered_exchange.json"), Charsets.UTF_8));
        int count = 0;
        List<Integer> partitionRecordCounts = Lists.newArrayList();
        for (QueryDataBatch b : results) {
            if (b.getData() != null) {
                int rows = b.getHeader().getRowCount();
                count += rows;
                DrillConfig config = DrillConfig.create();
                RecordBatchLoader loader = new RecordBatchLoader(new BootStrapContext(config, ClassPathScanner.fromPrescan(config)).getAllocator());
                loader.load(b.getHeader().getDef(), b.getData());
                BigIntVector vv1 = (BigIntVector) loader.getValueAccessorById(BigIntVector.class, loader.getValueVectorId(new SchemaPath("col1", ExpressionPosition.UNKNOWN)).getFieldIds()).getValueVector();
                Float8Vector vv2 = (Float8Vector) loader.getValueAccessorById(Float8Vector.class, loader.getValueVectorId(new SchemaPath("col2", ExpressionPosition.UNKNOWN)).getFieldIds()).getValueVector();
                IntVector pVector = (IntVector) loader.getValueAccessorById(IntVector.class, loader.getValueVectorId(new SchemaPath("partition", ExpressionPosition.UNKNOWN)).getFieldIds()).getValueVector();
                long previous1 = Long.MIN_VALUE;
                double previous2 = Double.MIN_VALUE;
                int partPrevious = -1;
                long current1 = Long.MIN_VALUE;
                double current2 = Double.MIN_VALUE;
                int partCurrent = -1;
                int partitionRecordCount = 0;
                for (int i = 0; i < rows; i++) {
                    previous1 = current1;
                    previous2 = current2;
                    partPrevious = partCurrent;
                    current1 = vv1.getAccessor().get(i);
                    current2 = vv2.getAccessor().get(i);
                    partCurrent = pVector.getAccessor().get(i);
                    Assert.assertTrue(current1 >= previous1);
                    if (current1 == previous1) {
                        Assert.assertTrue(current2 <= previous2);
                    }
                    if (partCurrent == partPrevious || partPrevious == -1) {
                        partitionRecordCount++;
                    } else {
                        partitionRecordCounts.add(partitionRecordCount);
                        partitionRecordCount = 0;
                    }
                }
                partitionRecordCounts.add(partitionRecordCount);
                loader.clear();
            }
            b.release();
        }
        double[] values = new double[partitionRecordCounts.size()];
        int i = 0;
        for (Integer rc : partitionRecordCounts) {
            values[i++] = rc.doubleValue();
        }
        StandardDeviation stdDev = new StandardDeviation();
        Mean mean = new Mean();
        double std = stdDev.evaluate(values);
        double m = mean.evaluate(values);
        System.out.println("mean: " + m + " std dev: " + std);
        //Assert.assertTrue(std < 0.1 * m);
        assertEquals(31000, count);
    }
}
Also used : Mean(org.apache.commons.math.stat.descriptive.moment.Mean) BigIntVector(org.apache.drill.exec.vector.BigIntVector) IntVector(org.apache.drill.exec.vector.IntVector) RecordBatchLoader(org.apache.drill.exec.record.RecordBatchLoader) Float8Vector(org.apache.drill.exec.vector.Float8Vector) BigIntVector(org.apache.drill.exec.vector.BigIntVector) QueryDataBatch(org.apache.drill.exec.rpc.user.QueryDataBatch) DrillConfig(org.apache.drill.common.config.DrillConfig) Drillbit(org.apache.drill.exec.server.Drillbit) SchemaPath(org.apache.drill.common.expression.SchemaPath) RemoteServiceSet(org.apache.drill.exec.server.RemoteServiceSet) BootStrapContext(org.apache.drill.exec.server.BootStrapContext) StandardDeviation(org.apache.commons.math.stat.descriptive.moment.StandardDeviation) DrillClient(org.apache.drill.exec.client.DrillClient) Test(org.junit.Test)

Example 67 with SchemaPath

use of org.apache.drill.common.expression.SchemaPath in project drill by apache.

the class TestSimpleExternalSort method validateResults.

private void validateResults(BufferAllocator allocator, List<QueryDataBatch> results) throws SchemaChangeException {
    long previousBigInt = Long.MAX_VALUE;
    int recordCount = 0;
    int batchCount = 0;
    for (QueryDataBatch b : results) {
        RecordBatchLoader loader = new RecordBatchLoader(allocator);
        if (b.getHeader().getRowCount() > 0) {
            batchCount++;
            loader.load(b.getHeader().getDef(), b.getData());
            @SuppressWarnings("resource") BigIntVector c1 = (BigIntVector) loader.getValueAccessorById(BigIntVector.class, loader.getValueVectorId(new SchemaPath("blue", ExpressionPosition.UNKNOWN)).getFieldIds()).getValueVector();
            BigIntVector.Accessor a1 = c1.getAccessor();
            for (int i = 0; i < c1.getAccessor().getValueCount(); i++) {
                recordCount++;
                assertTrue(String.format("%d > %d", previousBigInt, a1.get(i)), previousBigInt >= a1.get(i));
                previousBigInt = a1.get(i);
            }
        }
        loader.clear();
        b.release();
    }
    System.out.println(String.format("Sorted %,d records in %d batches.", recordCount, batchCount));
}
Also used : QueryDataBatch(org.apache.drill.exec.rpc.user.QueryDataBatch) SchemaPath(org.apache.drill.common.expression.SchemaPath) RecordBatchLoader(org.apache.drill.exec.record.RecordBatchLoader) BigIntVector(org.apache.drill.exec.vector.BigIntVector)

Example 68 with SchemaPath

use of org.apache.drill.common.expression.SchemaPath in project drill by apache.

the class ExpressionTreeMaterializerTest method testMaterializingLateboundTreeValidated.

@Test
public void testMaterializingLateboundTreeValidated(@Injectable final RecordBatch batch) throws SchemaChangeException {
    ErrorCollector ec = new ErrorCollector() {

        int errorCount = 0;

        @Override
        public void addGeneralError(ExpressionPosition expr, String s) {
            errorCount++;
        }

        @Override
        public void addUnexpectedArgumentType(ExpressionPosition expr, String name, MajorType actual, MajorType[] expected, int argumentIndex) {
            errorCount++;
        }

        @Override
        public void addUnexpectedArgumentCount(ExpressionPosition expr, int actual, Range<Integer> expected) {
            errorCount++;
        }

        @Override
        public void addUnexpectedArgumentCount(ExpressionPosition expr, int actual, int expected) {
            errorCount++;
        }

        @Override
        public void addNonNumericType(ExpressionPosition expr, MajorType actual) {
            errorCount++;
        }

        @Override
        public void addUnexpectedType(ExpressionPosition expr, int index, MajorType actual) {
            errorCount++;
        }

        @Override
        public void addExpectedConstantValue(ExpressionPosition expr, int actual, String s) {
            errorCount++;
        }

        @Override
        public boolean hasErrors() {
            return errorCount > 0;
        }

        @Override
        public String toErrorString() {
            return String.format("Found %s errors.", errorCount);
        }

        @Override
        public int getErrorCount() {
            return errorCount;
        }
    };
    new NonStrictExpectations() {

        {
            batch.getValueVectorId(new SchemaPath("test", ExpressionPosition.UNKNOWN));
            result = new TypedFieldId(Types.required(MinorType.BIGINT), -5);
        }
    };
    new MockUp<RemoteFunctionRegistry>() {

        @Mock
        long getRegistryVersion() {
            return 0L;
        }
    };
    LogicalExpression functionCallExpr = new FunctionCall("testFunc", ImmutableList.of((LogicalExpression) new FieldReference("test", ExpressionPosition.UNKNOWN)), ExpressionPosition.UNKNOWN);
    LogicalExpression newExpr = ExpressionTreeMaterializer.materialize(functionCallExpr, batch, ec, registry);
    assertTrue(newExpr instanceof TypedNullConstant);
    assertEquals(1, ec.getErrorCount());
    System.out.println(ec.toErrorString());
}
Also used : FieldReference(org.apache.drill.common.expression.FieldReference) MajorType(org.apache.drill.common.types.TypeProtos.MajorType) ErrorCollector(org.apache.drill.common.expression.ErrorCollector) MockUp(mockit.MockUp) TypedNullConstant(org.apache.drill.common.expression.TypedNullConstant) Range(com.google.common.collect.Range) LogicalExpression(org.apache.drill.common.expression.LogicalExpression) SchemaPath(org.apache.drill.common.expression.SchemaPath) FunctionCall(org.apache.drill.common.expression.FunctionCall) ExpressionPosition(org.apache.drill.common.expression.ExpressionPosition) NonStrictExpectations(mockit.NonStrictExpectations) ExecTest(org.apache.drill.exec.ExecTest) Test(org.junit.Test)

Example 69 with SchemaPath

use of org.apache.drill.common.expression.SchemaPath in project drill by apache.

the class TestMathFunctions method testBasicMathFunctions.

@Test
public void testBasicMathFunctions(@Injectable final DrillbitContext bitContext, @Injectable UserClientConnection connection) throws Throwable {
    mockDrillbitContext(bitContext);
    final PhysicalPlanReader reader = PhysicalPlanReaderTestFactory.defaultPhysicalPlanReader(c);
    final PhysicalPlan plan = reader.readPhysicalPlan(Files.toString(FileUtils.getResourceAsFile("/functions/simple_math_functions.json"), Charsets.UTF_8));
    final FunctionImplementationRegistry registry = new FunctionImplementationRegistry(c);
    final FragmentContext context = new FragmentContext(bitContext, BitControl.PlanFragment.getDefaultInstance(), connection, registry);
    final SimpleRootExec exec = new SimpleRootExec(ImplCreator.getExec(context, (FragmentRoot) plan.getSortedOperators(false).iterator().next()));
    while (exec.next()) {
        final IntVector intMulVector = exec.getValueVectorById(new SchemaPath("INTMUL", ExpressionPosition.UNKNOWN), IntVector.class);
        final Float8Vector floatMulVector = exec.getValueVectorById(new SchemaPath("FLOATMUL", ExpressionPosition.UNKNOWN), Float8Vector.class);
        final IntVector intAddVector = exec.getValueVectorById(new SchemaPath("INTADD", ExpressionPosition.UNKNOWN), IntVector.class);
        final Float8Vector floatAddVector = exec.getValueVectorById(new SchemaPath("FLOATADD", ExpressionPosition.UNKNOWN), Float8Vector.class);
        assertEquals(exec.getRecordCount(), 1);
        assertEquals(intMulVector.getAccessor().get(0), 2);
        assertEquals(floatMulVector.getAccessor().get(0), (1.1 * 2.2), 0);
        assertEquals(intAddVector.getAccessor().get(0), 3);
        assertEquals(floatAddVector.getAccessor().get(0), (1.1 + 2.2), 0);
    }
    if (context.getFailureCause() != null) {
        throw context.getFailureCause();
    }
    assertTrue(!context.isFailed());
}
Also used : SimpleRootExec(org.apache.drill.exec.physical.impl.SimpleRootExec) PhysicalPlan(org.apache.drill.exec.physical.PhysicalPlan) FragmentContext(org.apache.drill.exec.ops.FragmentContext) IntVector(org.apache.drill.exec.vector.IntVector) SchemaPath(org.apache.drill.common.expression.SchemaPath) PhysicalPlanReader(org.apache.drill.exec.planner.PhysicalPlanReader) Float8Vector(org.apache.drill.exec.vector.Float8Vector) FragmentRoot(org.apache.drill.exec.physical.base.FragmentRoot) FunctionImplementationRegistry(org.apache.drill.exec.expr.fn.FunctionImplementationRegistry) Test(org.junit.Test) ExecTest(org.apache.drill.exec.ExecTest)

Example 70 with SchemaPath

use of org.apache.drill.common.expression.SchemaPath in project drill by apache.

the class TestCastFunctions method testCastVarBinary.

@Test
public //cast to varbinary(length)
void testCastVarBinary(@Injectable final DrillbitContext bitContext, @Injectable UserClientConnection connection) throws Throwable {
    mockDrillbitContext(bitContext);
    final PhysicalPlanReader reader = PhysicalPlanReaderTestFactory.defaultPhysicalPlanReader(CONFIG);
    final PhysicalPlan plan = reader.readPhysicalPlan(Files.toString(FileUtils.getResourceAsFile("/functions/cast/testCastVarBinary.json"), Charsets.UTF_8));
    final FunctionImplementationRegistry registry = new FunctionImplementationRegistry(CONFIG);
    final FragmentContext context = new FragmentContext(bitContext, PlanFragment.getDefaultInstance(), connection, registry);
    final SimpleRootExec exec = new SimpleRootExec(ImplCreator.getExec(context, (FragmentRoot) plan.getSortedOperators(false).iterator().next()));
    while (exec.next()) {
        final VarBinaryVector c0 = exec.getValueVectorById(new SchemaPath("int_lit_cast", ExpressionPosition.UNKNOWN), VarBinaryVector.class);
        final VarBinaryVector.Accessor a0 = c0.getAccessor();
        int count = 0;
        for (int i = 0; i < c0.getAccessor().getValueCount(); i++) {
            final VarBinaryHolder holder0 = new VarBinaryHolder();
            a0.get(i, holder0);
            assertEquals("123", StringFunctionHelpers.toStringFromUTF8(holder0.start, holder0.end, holder0.buffer));
            ++count;
        }
        assertEquals(5, count);
    }
    exec.close();
    context.close();
    if (context.getFailureCause() != null) {
        throw context.getFailureCause();
    }
    assertTrue(!context.isFailed());
}
Also used : PhysicalPlan(org.apache.drill.exec.physical.PhysicalPlan) FragmentContext(org.apache.drill.exec.ops.FragmentContext) SchemaPath(org.apache.drill.common.expression.SchemaPath) PhysicalPlanReader(org.apache.drill.exec.planner.PhysicalPlanReader) VarBinaryHolder(org.apache.drill.exec.expr.holders.VarBinaryHolder) FragmentRoot(org.apache.drill.exec.physical.base.FragmentRoot) FunctionImplementationRegistry(org.apache.drill.exec.expr.fn.FunctionImplementationRegistry) VarBinaryVector(org.apache.drill.exec.vector.VarBinaryVector) Test(org.junit.Test)

Aggregations

SchemaPath (org.apache.drill.common.expression.SchemaPath)74 Test (org.junit.Test)23 FunctionImplementationRegistry (org.apache.drill.exec.expr.fn.FunctionImplementationRegistry)17 FragmentContext (org.apache.drill.exec.ops.FragmentContext)16 PhysicalPlan (org.apache.drill.exec.physical.PhysicalPlan)15 FragmentRoot (org.apache.drill.exec.physical.base.FragmentRoot)15 PhysicalPlanReader (org.apache.drill.exec.planner.PhysicalPlanReader)15 LogicalExpression (org.apache.drill.common.expression.LogicalExpression)12 ExecTest (org.apache.drill.exec.ExecTest)12 BigIntVector (org.apache.drill.exec.vector.BigIntVector)9 ExecutionSetupException (org.apache.drill.common.exceptions.ExecutionSetupException)8 IntVector (org.apache.drill.exec.vector.IntVector)8 Path (org.apache.hadoop.fs.Path)8 SchemaChangeException (org.apache.drill.exec.exception.SchemaChangeException)7 ValueVector (org.apache.drill.exec.vector.ValueVector)7 IOException (java.io.IOException)6 ErrorCollector (org.apache.drill.common.expression.ErrorCollector)6 TypedFieldId (org.apache.drill.exec.record.TypedFieldId)6 ErrorCollectorImpl (org.apache.drill.common.expression.ErrorCollectorImpl)5 FieldReference (org.apache.drill.common.expression.FieldReference)5