Search in sources :

Example 31 with IBinaryComparatorFactory

use of org.apache.hyracks.api.dataflow.value.IBinaryComparatorFactory in project asterixdb by apache.

the class PreSortedDistinctByPOperator method contributeRuntimeOperator.

@Override
public void contributeRuntimeOperator(IHyracksJobBuilder builder, JobGenContext context, ILogicalOperator op, IOperatorSchema opSchema, IOperatorSchema[] inputSchemas, IOperatorSchema outerPlanSchema) throws AlgebricksException {
    IOperatorDescriptorRegistry spec = builder.getJobSpec();
    int[] keys = JobGenHelper.variablesToFieldIndexes(columnList, inputSchemas[0]);
    int sz = inputSchemas[0].getSize();
    int fdSz = sz - columnList.size();
    int[] fdColumns = new int[fdSz];
    int j = 0;
    for (LogicalVariable v : inputSchemas[0]) {
        if (!columnList.contains(v)) {
            fdColumns[j++] = inputSchemas[0].findVariable(v);
        }
    }
    int[] keysAndDecs = new int[keys.length + fdColumns.length];
    for (int i = 0; i < keys.length; i++) {
        keysAndDecs[i] = keys[i];
    }
    for (int i = 0; i < fdColumns.length; i++) {
        keysAndDecs[i + keys.length] = fdColumns[i];
    }
    IBinaryComparatorFactory[] comparatorFactories = JobGenHelper.variablesToAscBinaryComparatorFactories(columnList, context.getTypeEnvironment(op), context);
    IAggregateEvaluatorFactory[] aggFactories = new IAggregateEvaluatorFactory[] {};
    IAggregatorDescriptorFactory aggregatorFactory = new SimpleAlgebricksAccumulatingAggregatorFactory(aggFactories, keysAndDecs);
    RecordDescriptor recordDescriptor = JobGenHelper.mkRecordDescriptor(context.getTypeEnvironment(op), opSchema, context);
    /** make fd columns part of the key but the comparator only compares the distinct key columns */
    PreclusteredGroupOperatorDescriptor opDesc = new PreclusteredGroupOperatorDescriptor(spec, keysAndDecs, comparatorFactories, aggregatorFactory, recordDescriptor);
    contributeOpDesc(builder, (AbstractLogicalOperator) op, opDesc);
    ILogicalOperator src = op.getInputs().get(0).getValue();
    builder.contributeGraphEdge(src, 0, op, 0);
}
Also used : LogicalVariable(org.apache.hyracks.algebricks.core.algebra.base.LogicalVariable) RecordDescriptor(org.apache.hyracks.api.dataflow.value.RecordDescriptor) ILogicalOperator(org.apache.hyracks.algebricks.core.algebra.base.ILogicalOperator) IBinaryComparatorFactory(org.apache.hyracks.api.dataflow.value.IBinaryComparatorFactory) SimpleAlgebricksAccumulatingAggregatorFactory(org.apache.hyracks.algebricks.runtime.operators.aggreg.SimpleAlgebricksAccumulatingAggregatorFactory) IOperatorDescriptorRegistry(org.apache.hyracks.api.job.IOperatorDescriptorRegistry) IAggregateEvaluatorFactory(org.apache.hyracks.algebricks.runtime.base.IAggregateEvaluatorFactory) IAggregatorDescriptorFactory(org.apache.hyracks.dataflow.std.group.IAggregatorDescriptorFactory) PreclusteredGroupOperatorDescriptor(org.apache.hyracks.dataflow.std.group.preclustered.PreclusteredGroupOperatorDescriptor)

Example 32 with IBinaryComparatorFactory

use of org.apache.hyracks.api.dataflow.value.IBinaryComparatorFactory in project asterixdb by apache.

the class PreclusteredGroupByPOperator method contributeRuntimeOperator.

@Override
public void contributeRuntimeOperator(IHyracksJobBuilder builder, JobGenContext context, ILogicalOperator op, IOperatorSchema opSchema, IOperatorSchema[] inputSchemas, IOperatorSchema outerPlanSchema) throws AlgebricksException {
    int[] keys = JobGenHelper.variablesToFieldIndexes(columnList, inputSchemas[0]);
    GroupByOperator gby = (GroupByOperator) op;
    int[] fdColumns = getFdColumns(gby, inputSchemas[0]);
    // compile subplans and set the gby op. schema accordingly
    AlgebricksPipeline[] subplans = compileSubplans(inputSchemas[0], gby, opSchema, context);
    IAggregatorDescriptorFactory aggregatorFactory;
    if (gby.getNestedPlans().get(0).getRoots().get(0).getValue().getOperatorTag() == LogicalOperatorTag.RUNNINGAGGREGATE) {
        aggregatorFactory = new NestedPlansRunningAggregatorFactory(subplans, keys, fdColumns);
    } else {
        aggregatorFactory = new NestedPlansAccumulatingAggregatorFactory(subplans, keys, fdColumns);
    }
    IOperatorDescriptorRegistry spec = builder.getJobSpec();
    IBinaryComparatorFactory[] comparatorFactories = JobGenHelper.variablesToAscBinaryComparatorFactories(columnList, context.getTypeEnvironment(op), context);
    RecordDescriptor recordDescriptor = JobGenHelper.mkRecordDescriptor(context.getTypeEnvironment(op), opSchema, context);
    PreclusteredGroupOperatorDescriptor opDesc = new PreclusteredGroupOperatorDescriptor(spec, keys, comparatorFactories, aggregatorFactory, recordDescriptor, groupAll);
    contributeOpDesc(builder, (AbstractLogicalOperator) op, opDesc);
    ILogicalOperator src = op.getInputs().get(0).getValue();
    builder.contributeGraphEdge(src, 0, op, 0);
}
Also used : GroupByOperator(org.apache.hyracks.algebricks.core.algebra.operators.logical.GroupByOperator) RecordDescriptor(org.apache.hyracks.api.dataflow.value.RecordDescriptor) ILogicalOperator(org.apache.hyracks.algebricks.core.algebra.base.ILogicalOperator) IBinaryComparatorFactory(org.apache.hyracks.api.dataflow.value.IBinaryComparatorFactory) NestedPlansAccumulatingAggregatorFactory(org.apache.hyracks.algebricks.runtime.operators.aggreg.NestedPlansAccumulatingAggregatorFactory) IOperatorDescriptorRegistry(org.apache.hyracks.api.job.IOperatorDescriptorRegistry) IAggregatorDescriptorFactory(org.apache.hyracks.dataflow.std.group.IAggregatorDescriptorFactory) NestedPlansRunningAggregatorFactory(org.apache.hyracks.algebricks.runtime.operators.aggreg.NestedPlansRunningAggregatorFactory) PreclusteredGroupOperatorDescriptor(org.apache.hyracks.dataflow.std.group.preclustered.PreclusteredGroupOperatorDescriptor) AlgebricksPipeline(org.apache.hyracks.algebricks.runtime.base.AlgebricksPipeline)

Example 33 with IBinaryComparatorFactory

use of org.apache.hyracks.api.dataflow.value.IBinaryComparatorFactory in project asterixdb by apache.

the class DataflowTest method testHDFSReadWriteOperators.

/**
     * Test a job with only HDFS read and writes.
     *
     * @throws Exception
     */
public void testHDFSReadWriteOperators() throws Exception {
    FileInputFormat.setInputPaths(conf, HDFS_INPUT_PATH);
    FileOutputFormat.setOutputPath(conf, new Path(HDFS_OUTPUT_PATH));
    conf.setInputFormat(TextInputFormat.class);
    Scheduler scheduler = new Scheduler(HyracksUtils.CC_HOST, HyracksUtils.TEST_HYRACKS_CC_CLIENT_PORT);
    InputSplit[] splits = conf.getInputFormat().getSplits(conf, numberOfNC * 4);
    String[] readSchedule = scheduler.getLocationConstraints(splits);
    JobSpecification jobSpec = new JobSpecification();
    RecordDescriptor recordDesc = new RecordDescriptor(new ISerializerDeserializer[] { new UTF8StringSerializerDeserializer() });
    String[] locations = new String[] { HyracksUtils.NC1_ID, HyracksUtils.NC1_ID, HyracksUtils.NC2_ID, HyracksUtils.NC2_ID };
    HDFSReadOperatorDescriptor readOperator = new HDFSReadOperatorDescriptor(jobSpec, recordDesc, conf, splits, readSchedule, new TextKeyValueParserFactory());
    PartitionConstraintHelper.addAbsoluteLocationConstraint(jobSpec, readOperator, locations);
    ExternalSortOperatorDescriptor sortOperator = new ExternalSortOperatorDescriptor(jobSpec, 10, new int[] { 0 }, new IBinaryComparatorFactory[] { RawBinaryComparatorFactory.INSTANCE }, recordDesc);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(jobSpec, sortOperator, locations);
    HDFSWriteOperatorDescriptor writeOperator = new HDFSWriteOperatorDescriptor(jobSpec, conf, new TextTupleWriterFactory());
    PartitionConstraintHelper.addAbsoluteLocationConstraint(jobSpec, writeOperator, HyracksUtils.NC1_ID);
    jobSpec.connect(new OneToOneConnectorDescriptor(jobSpec), readOperator, 0, sortOperator, 0);
    jobSpec.connect(new MToNPartitioningMergingConnectorDescriptor(jobSpec, new FieldHashPartitionComputerFactory(new int[] { 0 }, new IBinaryHashFunctionFactory[] { RawBinaryHashFunctionFactory.INSTANCE }), new int[] { 0 }, new IBinaryComparatorFactory[] { RawBinaryComparatorFactory.INSTANCE }, null), sortOperator, 0, writeOperator, 0);
    jobSpec.addRoot(writeOperator);
    IHyracksClientConnection client = new HyracksConnection(HyracksUtils.CC_HOST, HyracksUtils.TEST_HYRACKS_CC_CLIENT_PORT);
    JobId jobId = client.startJob(jobSpec);
    client.waitForCompletion(jobId);
    Assert.assertEquals(true, checkResults());
}
Also used : Path(org.apache.hadoop.fs.Path) IHyracksClientConnection(org.apache.hyracks.api.client.IHyracksClientConnection) Scheduler(org.apache.hyracks.hdfs.scheduler.Scheduler) RecordDescriptor(org.apache.hyracks.api.dataflow.value.RecordDescriptor) MToNPartitioningMergingConnectorDescriptor(org.apache.hyracks.dataflow.std.connectors.MToNPartitioningMergingConnectorDescriptor) IBinaryComparatorFactory(org.apache.hyracks.api.dataflow.value.IBinaryComparatorFactory) OneToOneConnectorDescriptor(org.apache.hyracks.dataflow.std.connectors.OneToOneConnectorDescriptor) UTF8StringSerializerDeserializer(org.apache.hyracks.dataflow.common.data.marshalling.UTF8StringSerializerDeserializer) FieldHashPartitionComputerFactory(org.apache.hyracks.dataflow.common.data.partition.FieldHashPartitionComputerFactory) TextTupleWriterFactory(org.apache.hyracks.hdfs.lib.TextTupleWriterFactory) ExternalSortOperatorDescriptor(org.apache.hyracks.dataflow.std.sort.ExternalSortOperatorDescriptor) JobSpecification(org.apache.hyracks.api.job.JobSpecification) HyracksConnection(org.apache.hyracks.api.client.HyracksConnection) InputSplit(org.apache.hadoop.mapred.InputSplit) TextKeyValueParserFactory(org.apache.hyracks.hdfs.lib.TextKeyValueParserFactory) JobId(org.apache.hyracks.api.job.JobId)

Example 34 with IBinaryComparatorFactory

use of org.apache.hyracks.api.dataflow.value.IBinaryComparatorFactory in project asterixdb by apache.

the class Join method createJob.

private static JobSpecification createJob(FileSplit[] customerSplits, FileSplit[] orderSplits, FileSplit[] resultSplits, int numJoinPartitions, String algo, int graceInputSize, int graceRecordsPerFrame, double graceFactor, int memSize, int tableSize, boolean hasGroupBy, int frameSize) throws HyracksDataException {
    JobSpecification spec = new JobSpecification(frameSize);
    IFileSplitProvider custSplitsProvider = new ConstantFileSplitProvider(customerSplits);
    long custFileSize = 0;
    for (int i = 0; i < customerSplits.length; i++) {
        custFileSize += customerSplits[i].getFile(null).length();
    }
    IFileSplitProvider ordersSplitsProvider = new ConstantFileSplitProvider(orderSplits);
    long orderFileSize = 0;
    for (int i = 0; i < orderSplits.length; i++) {
        orderFileSize += orderSplits[i].getFile(null).length();
    }
    FileScanOperatorDescriptor ordScanner = new FileScanOperatorDescriptor(spec, ordersSplitsProvider, new DelimitedDataTupleParserFactory(orderParserFactories, '|'), Common.ordersDesc);
    createPartitionConstraint(spec, ordScanner, orderSplits);
    FileScanOperatorDescriptor custScanner = new FileScanOperatorDescriptor(spec, custSplitsProvider, new DelimitedDataTupleParserFactory(custParserFactories, '|'), Common.custDesc);
    createPartitionConstraint(spec, custScanner, customerSplits);
    IOperatorDescriptor join;
    if ("nestedloop".equalsIgnoreCase(algo)) {
        join = new NestedLoopJoinOperatorDescriptor(spec, new JoinComparatorFactory(PointableBinaryComparatorFactory.of(UTF8StringPointable.FACTORY), 0, 1), Common.custOrderJoinDesc, memSize, false, null);
    } else if ("inmem".equalsIgnoreCase(algo)) {
        join = new InMemoryHashJoinOperatorDescriptor(spec, new int[] { 0 }, new int[] { 1 }, new IBinaryHashFunctionFactory[] { PointableBinaryHashFunctionFactory.of(UTF8StringPointable.FACTORY) }, new IBinaryComparatorFactory[] { PointableBinaryComparatorFactory.of(UTF8StringPointable.FACTORY) }, Common.custOrderJoinDesc, tableSize, null, memSize * frameSize);
    } else if ("hybrid".equalsIgnoreCase(algo)) {
        join = new OptimizedHybridHashJoinOperatorDescriptor(spec, memSize, graceInputSize, graceFactor, new int[] { 0 }, new int[] { 1 }, new IBinaryHashFunctionFamily[] { UTF8StringBinaryHashFunctionFamily.INSTANCE }, new IBinaryComparatorFactory[] { PointableBinaryComparatorFactory.of(UTF8StringPointable.FACTORY) }, Common.custOrderJoinDesc, new JoinComparatorFactory(PointableBinaryComparatorFactory.of(UTF8StringPointable.FACTORY), 0, 1), new JoinComparatorFactory(PointableBinaryComparatorFactory.of(UTF8StringPointable.FACTORY), 1, 0), null);
    } else {
        System.err.println("unknown algorithm:" + algo);
        return null;
    }
    PartitionConstraintHelper.addPartitionCountConstraint(spec, join, numJoinPartitions);
    IConnectorDescriptor ordJoinConn = new MToNPartitioningConnectorDescriptor(spec, new FieldHashPartitionComputerFactory(new int[] { 1 }, new IBinaryHashFunctionFactory[] { PointableBinaryHashFunctionFactory.of(UTF8StringPointable.FACTORY) }));
    spec.connect(ordJoinConn, ordScanner, 0, join, 1);
    IConnectorDescriptor custJoinConn = new MToNPartitioningConnectorDescriptor(spec, new FieldHashPartitionComputerFactory(new int[] { 0 }, new IBinaryHashFunctionFactory[] { PointableBinaryHashFunctionFactory.of(UTF8StringPointable.FACTORY) }));
    spec.connect(custJoinConn, custScanner, 0, join, 0);
    IOperatorDescriptor endingOp = join;
    if (hasGroupBy) {
        RecordDescriptor groupResultDesc = new RecordDescriptor(new ISerializerDeserializer[] { new UTF8StringSerializerDeserializer(), IntegerSerializerDeserializer.INSTANCE });
        ExternalGroupOperatorDescriptor gby = new ExternalGroupOperatorDescriptor(spec, tableSize, custFileSize + orderFileSize, new int[] { 6 }, memSize, new IBinaryComparatorFactory[] { PointableBinaryComparatorFactory.of(UTF8StringPointable.FACTORY) }, new UTF8StringNormalizedKeyComputerFactory(), new MultiFieldsAggregatorFactory(new IFieldAggregateDescriptorFactory[] { new IntSumFieldAggregatorFactory(1, false), new IntSumFieldAggregatorFactory(3, false), new FloatSumFieldAggregatorFactory(5, false) }), new MultiFieldsAggregatorFactory(new IFieldAggregateDescriptorFactory[] { new IntSumFieldAggregatorFactory(1, false), new IntSumFieldAggregatorFactory(2, false), new FloatSumFieldAggregatorFactory(3, false) }), groupResultDesc, groupResultDesc, new HashSpillableTableFactory(new IBinaryHashFunctionFamily[] { UTF8StringBinaryHashFunctionFamily.INSTANCE }));
        createPartitionConstraint(spec, gby, resultSplits);
        IConnectorDescriptor joinGroupConn = new MToNPartitioningConnectorDescriptor(spec, new FieldHashPartitionComputerFactory(new int[] { 6 }, new IBinaryHashFunctionFactory[] { PointableBinaryHashFunctionFactory.of(UTF8StringPointable.FACTORY) }));
        spec.connect(joinGroupConn, join, 0, gby, 0);
        endingOp = gby;
    }
    IFileSplitProvider outSplitProvider = new ConstantFileSplitProvider(resultSplits);
    //FrameFileWriterOperatorDescriptor writer = new FrameFileWriterOperatorDescriptor(spec, outSplitProvider);
    IOperatorDescriptor writer = new PlainFileWriterOperatorDescriptor(spec, outSplitProvider, "|");
    createPartitionConstraint(spec, writer, resultSplits);
    IConnectorDescriptor endingPrinterConn = new OneToOneConnectorDescriptor(spec);
    spec.connect(endingPrinterConn, endingOp, 0, writer, 0);
    spec.addRoot(writer);
    return spec;
}
Also used : OptimizedHybridHashJoinOperatorDescriptor(org.apache.hyracks.dataflow.std.join.OptimizedHybridHashJoinOperatorDescriptor) IFileSplitProvider(org.apache.hyracks.dataflow.std.file.IFileSplitProvider) RecordDescriptor(org.apache.hyracks.api.dataflow.value.RecordDescriptor) HashSpillableTableFactory(org.apache.hyracks.dataflow.std.group.HashSpillableTableFactory) JoinComparatorFactory(org.apache.hyracks.dataflow.std.join.JoinComparatorFactory) OneToOneConnectorDescriptor(org.apache.hyracks.dataflow.std.connectors.OneToOneConnectorDescriptor) UTF8StringSerializerDeserializer(org.apache.hyracks.dataflow.common.data.marshalling.UTF8StringSerializerDeserializer) IBinaryHashFunctionFactory(org.apache.hyracks.api.dataflow.value.IBinaryHashFunctionFactory) NestedLoopJoinOperatorDescriptor(org.apache.hyracks.dataflow.std.join.NestedLoopJoinOperatorDescriptor) FileScanOperatorDescriptor(org.apache.hyracks.dataflow.std.file.FileScanOperatorDescriptor) JobSpecification(org.apache.hyracks.api.job.JobSpecification) IBinaryHashFunctionFamily(org.apache.hyracks.api.dataflow.value.IBinaryHashFunctionFamily) IFieldAggregateDescriptorFactory(org.apache.hyracks.dataflow.std.group.IFieldAggregateDescriptorFactory) IConnectorDescriptor(org.apache.hyracks.api.dataflow.IConnectorDescriptor) UTF8StringNormalizedKeyComputerFactory(org.apache.hyracks.dataflow.common.data.normalizers.UTF8StringNormalizedKeyComputerFactory) MultiFieldsAggregatorFactory(org.apache.hyracks.dataflow.std.group.aggregators.MultiFieldsAggregatorFactory) ExternalGroupOperatorDescriptor(org.apache.hyracks.dataflow.std.group.external.ExternalGroupOperatorDescriptor) InMemoryHashJoinOperatorDescriptor(org.apache.hyracks.dataflow.std.join.InMemoryHashJoinOperatorDescriptor) ConstantFileSplitProvider(org.apache.hyracks.dataflow.std.file.ConstantFileSplitProvider) IBinaryComparatorFactory(org.apache.hyracks.api.dataflow.value.IBinaryComparatorFactory) MToNPartitioningConnectorDescriptor(org.apache.hyracks.dataflow.std.connectors.MToNPartitioningConnectorDescriptor) DelimitedDataTupleParserFactory(org.apache.hyracks.dataflow.std.file.DelimitedDataTupleParserFactory) FieldHashPartitionComputerFactory(org.apache.hyracks.dataflow.common.data.partition.FieldHashPartitionComputerFactory) Common.createPartitionConstraint(org.apache.hyracks.examples.tpch.client.Common.createPartitionConstraint) IOperatorDescriptor(org.apache.hyracks.api.dataflow.IOperatorDescriptor) PlainFileWriterOperatorDescriptor(org.apache.hyracks.dataflow.std.file.PlainFileWriterOperatorDescriptor) FloatSumFieldAggregatorFactory(org.apache.hyracks.dataflow.std.group.aggregators.FloatSumFieldAggregatorFactory) IntSumFieldAggregatorFactory(org.apache.hyracks.dataflow.std.group.aggregators.IntSumFieldAggregatorFactory)

Example 35 with IBinaryComparatorFactory

use of org.apache.hyracks.api.dataflow.value.IBinaryComparatorFactory in project asterixdb by apache.

the class DataflowTest method testHDFSReadWriteOperators.

/**
     * Test a job with only HDFS read and writes.
     *
     * @throws Exception
     */
@SuppressWarnings({ "rawtypes", "unchecked" })
public void testHDFSReadWriteOperators() throws Exception {
    FileInputFormat.setInputPaths(conf, HDFS_INPUT_PATH);
    FileOutputFormat.setOutputPath(conf, new Path(HDFS_OUTPUT_PATH));
    conf.setInputFormatClass(TextInputFormat.class);
    Scheduler scheduler = new Scheduler(HyracksUtils.CC_HOST, HyracksUtils.TEST_HYRACKS_CC_CLIENT_PORT);
    InputFormat inputFormat = ReflectionUtils.newInstance(conf.getInputFormatClass(), getConfiguration());
    List<InputSplit> splits = inputFormat.getSplits(conf);
    String[] readSchedule = scheduler.getLocationConstraints(splits);
    JobSpecification jobSpec = new JobSpecification();
    RecordDescriptor recordDesc = new RecordDescriptor(new ISerializerDeserializer[] { new UTF8StringSerializerDeserializer() });
    String[] locations = new String[] { HyracksUtils.NC1_ID, HyracksUtils.NC1_ID, HyracksUtils.NC2_ID, HyracksUtils.NC2_ID };
    HDFSReadOperatorDescriptor readOperator = new HDFSReadOperatorDescriptor(jobSpec, recordDesc, conf, splits, readSchedule, new TextKeyValueParserFactory());
    PartitionConstraintHelper.addAbsoluteLocationConstraint(jobSpec, readOperator, locations);
    ExternalSortOperatorDescriptor sortOperator = new ExternalSortOperatorDescriptor(jobSpec, 10, new int[] { 0 }, new IBinaryComparatorFactory[] { RawBinaryComparatorFactory.INSTANCE }, recordDesc);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(jobSpec, sortOperator, locations);
    HDFSWriteOperatorDescriptor writeOperator = new HDFSWriteOperatorDescriptor(jobSpec, conf, new TextTupleWriterFactory());
    PartitionConstraintHelper.addAbsoluteLocationConstraint(jobSpec, writeOperator, HyracksUtils.NC1_ID);
    jobSpec.connect(new OneToOneConnectorDescriptor(jobSpec), readOperator, 0, sortOperator, 0);
    jobSpec.connect(new MToNPartitioningMergingConnectorDescriptor(jobSpec, new FieldHashPartitionComputerFactory(new int[] { 0 }, new IBinaryHashFunctionFactory[] { RawBinaryHashFunctionFactory.INSTANCE }), new int[] { 0 }, new IBinaryComparatorFactory[] { RawBinaryComparatorFactory.INSTANCE }, null), sortOperator, 0, writeOperator, 0);
    jobSpec.addRoot(writeOperator);
    IHyracksClientConnection client = new HyracksConnection(HyracksUtils.CC_HOST, HyracksUtils.TEST_HYRACKS_CC_CLIENT_PORT);
    JobId jobId = client.startJob(jobSpec);
    client.waitForCompletion(jobId);
    Assert.assertEquals(true, checkResults());
}
Also used : Path(org.apache.hadoop.fs.Path) IHyracksClientConnection(org.apache.hyracks.api.client.IHyracksClientConnection) Scheduler(org.apache.hyracks.hdfs2.scheduler.Scheduler) RecordDescriptor(org.apache.hyracks.api.dataflow.value.RecordDescriptor) MToNPartitioningMergingConnectorDescriptor(org.apache.hyracks.dataflow.std.connectors.MToNPartitioningMergingConnectorDescriptor) IBinaryComparatorFactory(org.apache.hyracks.api.dataflow.value.IBinaryComparatorFactory) OneToOneConnectorDescriptor(org.apache.hyracks.dataflow.std.connectors.OneToOneConnectorDescriptor) UTF8StringSerializerDeserializer(org.apache.hyracks.dataflow.common.data.marshalling.UTF8StringSerializerDeserializer) FieldHashPartitionComputerFactory(org.apache.hyracks.dataflow.common.data.partition.FieldHashPartitionComputerFactory) TextTupleWriterFactory(org.apache.hyracks.hdfs.lib.TextTupleWriterFactory) TextInputFormat(org.apache.hadoop.mapreduce.lib.input.TextInputFormat) FileInputFormat(org.apache.hadoop.mapreduce.lib.input.FileInputFormat) InputFormat(org.apache.hadoop.mapreduce.InputFormat) ExternalSortOperatorDescriptor(org.apache.hyracks.dataflow.std.sort.ExternalSortOperatorDescriptor) JobSpecification(org.apache.hyracks.api.job.JobSpecification) HyracksConnection(org.apache.hyracks.api.client.HyracksConnection) InputSplit(org.apache.hadoop.mapreduce.InputSplit) TextKeyValueParserFactory(org.apache.hyracks.hdfs.lib.TextKeyValueParserFactory) JobId(org.apache.hyracks.api.job.JobId)

Aggregations

IBinaryComparatorFactory (org.apache.hyracks.api.dataflow.value.IBinaryComparatorFactory)86 ITypeTraits (org.apache.hyracks.api.dataflow.value.ITypeTraits)45 RecordDescriptor (org.apache.hyracks.api.dataflow.value.RecordDescriptor)25 ArrayTupleBuilder (org.apache.hyracks.dataflow.common.comm.io.ArrayTupleBuilder)25 Test (org.junit.Test)25 ISerializerDeserializer (org.apache.hyracks.api.dataflow.value.ISerializerDeserializer)24 ArrayTupleReference (org.apache.hyracks.dataflow.common.comm.io.ArrayTupleReference)22 HyracksDataException (org.apache.hyracks.api.exceptions.HyracksDataException)19 UTF8StringSerializerDeserializer (org.apache.hyracks.dataflow.common.data.marshalling.UTF8StringSerializerDeserializer)19 ITreeIndex (org.apache.hyracks.storage.am.common.api.ITreeIndex)17 IIndexAccessor (org.apache.hyracks.storage.common.IIndexAccessor)16 JobSpecification (org.apache.hyracks.api.job.JobSpecification)15 OneToOneConnectorDescriptor (org.apache.hyracks.dataflow.std.connectors.OneToOneConnectorDescriptor)15 IBinaryComparatorFactoryProvider (org.apache.hyracks.algebricks.data.IBinaryComparatorFactoryProvider)14 FieldHashPartitionComputerFactory (org.apache.hyracks.dataflow.common.data.partition.FieldHashPartitionComputerFactory)14 IFileSplitProvider (org.apache.hyracks.dataflow.std.file.IFileSplitProvider)13 LogicalVariable (org.apache.hyracks.algebricks.core.algebra.base.LogicalVariable)11 IVariableTypeEnvironment (org.apache.hyracks.algebricks.core.algebra.expressions.IVariableTypeEnvironment)11 MToNPartitioningMergingConnectorDescriptor (org.apache.hyracks.dataflow.std.connectors.MToNPartitioningMergingConnectorDescriptor)10 IPrimitiveValueProviderFactory (org.apache.hyracks.storage.am.common.api.IPrimitiveValueProviderFactory)10