Examples with DelimitedDataTupleParserFactory org.apache.hyracks.dataflow.std.file.DelimitedDataTupleParserFactory used on opensource projects

Example 36 with DelimitedDataTupleParserFactory

use of org.apache.hyracks.dataflow.std.file.DelimitedDataTupleParserFactory in project asterixdb by apache.

the class PushRuntimeTest method scanAggregateWrite.

@Test
public void scanAggregateWrite() throws Exception {
    JobSpecification spec = new JobSpecification(FRAME_SIZE);
    // the scanner
    FileSplit[] fileSplits = new FileSplit[1];
    fileSplits[0] = new ManagedFileSplit(AlgebricksHyracksIntegrationUtil.NC1_ID, "data" + File.separator + "tpch0.001" + File.separator + "customer-part1.tbl");
    IFileSplitProvider splitProvider = new ConstantFileSplitProvider(fileSplits);
    RecordDescriptor scannerDesc = new RecordDescriptor(new ISerializerDeserializer[] { IntegerSerializerDeserializer.INSTANCE, new UTF8StringSerializerDeserializer(), new UTF8StringSerializerDeserializer(), IntegerSerializerDeserializer.INSTANCE, new UTF8StringSerializerDeserializer(), FloatSerializerDeserializer.INSTANCE, new UTF8StringSerializerDeserializer(), new UTF8StringSerializerDeserializer() });
    IValueParserFactory[] valueParsers = new IValueParserFactory[] { IntegerParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, IntegerParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, FloatParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE };
    FileScanOperatorDescriptor scanner = new FileScanOperatorDescriptor(spec, splitProvider, new DelimitedDataTupleParserFactory(valueParsers, '|'), scannerDesc);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, scanner, new String[] { AlgebricksHyracksIntegrationUtil.NC1_ID });
    // the algebricks op.
    AggregateRuntimeFactory agg = new AggregateRuntimeFactory(new IAggregateEvaluatorFactory[] { new TupleCountAggregateFunctionFactory() });
    RecordDescriptor aggDesc = new RecordDescriptor(new ISerializerDeserializer[] { IntegerSerializerDeserializer.INSTANCE });
    String filePath = PATH_ACTUAL + SEPARATOR + "scanAggregateWrite.out";
    File outFile = new File(filePath);
    SinkWriterRuntimeFactory writer = new SinkWriterRuntimeFactory(new int[] { 0 }, new IPrinterFactory[] { IntegerPrinterFactory.INSTANCE }, outFile, PrinterBasedWriterFactory.INSTANCE, aggDesc);
    AlgebricksMetaOperatorDescriptor algebricksOp = new AlgebricksMetaOperatorDescriptor(spec, 1, 0, new IPushRuntimeFactory[] { agg, writer }, new RecordDescriptor[] { aggDesc, null });
    PartitionConstraintHelper.addPartitionCountConstraint(spec, algebricksOp, 1);
    spec.connect(new OneToOneConnectorDescriptor(spec), scanner, 0, algebricksOp, 0);
    spec.addRoot(algebricksOp);
    AlgebricksHyracksIntegrationUtil.runJob(spec);
    StringBuilder buf = new StringBuilder();
    readFileToString(outFile, buf);
    Assert.assertEquals("75", buf.toString());
    outFile.delete();
}

Example 37 with DelimitedDataTupleParserFactory

use of org.apache.hyracks.dataflow.std.file.DelimitedDataTupleParserFactory in project asterixdb by apache.

the class PushRuntimeTest method scanReplicateWrite.

@Test
public void scanReplicateWrite() throws Exception {
    final int outputArity = 2;
    JobSpecification spec = new JobSpecification(FRAME_SIZE);
    String inputFileName = "data" + File.separator + "tpch0.001" + File.separator + "customer.tbl";
    FileSplit[] inputSplits = new FileSplit[] { new ManagedFileSplit(AlgebricksHyracksIntegrationUtil.NC1_ID, inputFileName) };
    DelimitedDataTupleParserFactory stringParser = new DelimitedDataTupleParserFactory(new IValueParserFactory[] { UTF8StringParserFactory.INSTANCE }, '');
    RecordDescriptor stringRec = new RecordDescriptor(new ISerializerDeserializer[] { new UTF8StringSerializerDeserializer() });
    FileScanOperatorDescriptor scanOp = new FileScanOperatorDescriptor(spec, new ConstantFileSplitProvider(inputSplits), stringParser, stringRec);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, scanOp, new String[] { AlgebricksHyracksIntegrationUtil.NC1_ID });
    ReplicateOperatorDescriptor replicateOp = new ReplicateOperatorDescriptor(spec, stringRec, outputArity);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, replicateOp, new String[] { AlgebricksHyracksIntegrationUtil.NC1_ID });
    IOperatorDescriptor[] outputOp = new IOperatorDescriptor[outputArity];
    File[] outputFile = new File[outputArity];
    for (int i = 0; i < outputArity; i++) {
        FileSplit fileSplit = createFile(AlgebricksHyracksIntegrationUtil.nc1);
        outputFile[i] = fileSplit.getFile(AlgebricksHyracksIntegrationUtil.nc1.getIoManager());
        outputOp[i] = new LineFileWriteOperatorDescriptor(spec, new FileSplit[] { fileSplit });
        PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, outputOp[i], new String[] { AlgebricksHyracksIntegrationUtil.NC1_ID });
    }
    spec.connect(new OneToOneConnectorDescriptor(spec), scanOp, 0, replicateOp, 0);
    for (int i = 0; i < outputArity; i++) {
        spec.connect(new OneToOneConnectorDescriptor(spec), replicateOp, i, outputOp[i], 0);
    }
    for (int i = 0; i < outputArity; i++) {
        spec.addRoot(outputOp[i]);
    }
    AlgebricksHyracksIntegrationUtil.runJob(spec);
    for (int i = 0; i < outputArity; i++) {
        compareFiles("data" + File.separator + "device0" + File.separator + inputFileName, outputFile[i].getAbsolutePath());
    }
}

Example 38 with DelimitedDataTupleParserFactory

use of org.apache.hyracks.dataflow.std.file.DelimitedDataTupleParserFactory in project asterixdb by apache.

the class VSizeFrameSortMergeTest method sortTask.

public void sortTask(int frameSize, int frameLimit) throws Exception {
    JobSpecification spec = new JobSpecification();
    FileScanOperatorDescriptor ordScanner = new FileScanOperatorDescriptor(spec, ordersSplitProvider, new DelimitedDataTupleParserFactory(new IValueParserFactory[] { UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE }, '|'), ordersDesc);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, ordScanner, NC1_ID, NC2_ID);
    spec.setFrameSize(frameSize);
    ExternalSortOperatorDescriptor sorter = new ExternalSortOperatorDescriptor(spec, frameLimit, new int[] { 1, 0 }, new IBinaryComparatorFactory[] { PointableBinaryComparatorFactory.of(UTF8StringPointable.FACTORY), PointableBinaryComparatorFactory.of(UTF8StringPointable.FACTORY) }, ordersDesc);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, sorter, NC1_ID, NC2_ID);
    String path = getClass().getSimpleName() + aInteger.getAndIncrement() + ".tmp";
    IFileSplitProvider outputSplitProvider = new ConstantFileSplitProvider(new FileSplit[] { new ManagedFileSplit(NC1_ID, path) });
    IOperatorDescriptor printer = new PlainFileWriterOperatorDescriptor(spec, outputSplitProvider, "|");
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, printer, NC1_ID);
    spec.connect(new OneToOneConnectorDescriptor(spec), ordScanner, 0, sorter, 0);
    spec.connect(new MToNPartitioningMergingConnectorDescriptor(spec, new FieldHashPartitionComputerFactory(new int[] { 1, 0 }, new IBinaryHashFunctionFactory[] { PointableBinaryHashFunctionFactory.of(UTF8StringPointable.FACTORY), PointableBinaryHashFunctionFactory.of(UTF8StringPointable.FACTORY) }), new int[] { 1, 0 }, new IBinaryComparatorFactory[] { PointableBinaryComparatorFactory.of(UTF8StringPointable.FACTORY), PointableBinaryComparatorFactory.of(UTF8StringPointable.FACTORY) }, new UTF8StringNormalizedKeyComputerFactory()), sorter, 0, printer, 0);
    spec.addRoot(printer);
    runTest(spec);
    System.out.println("Result write into :" + path);
}

Example 39 with DelimitedDataTupleParserFactory

use of org.apache.hyracks.dataflow.std.file.DelimitedDataTupleParserFactory in project asterixdb by apache.

the class ReplicateOperatorTest method test.

@Test
public void test() throws Exception {
    final int outputArity = 2;
    JobSpecification spec = new JobSpecification();
    String inputFileName = "data" + File.separator + "nc1" + File.separator + "words.txt";
    File[] outputFile = new File[outputArity];
    for (int i = 0; i < outputArity; i++) {
        outputFile[i] = File.createTempFile("replicateop", null);
        outputFile[i].deleteOnExit();
    }
    FileSplit[] inputSplits = new FileSplit[] { new ManagedFileSplit(NC1_ID, inputFileName) };
    String[] locations = new String[] { NC1_ID };
    DelimitedDataTupleParserFactory stringParser = new DelimitedDataTupleParserFactory(new IValueParserFactory[] { UTF8StringParserFactory.INSTANCE }, '');
    RecordDescriptor stringRec = new RecordDescriptor(new ISerializerDeserializer[] { new UTF8StringSerializerDeserializer() });
    FileScanOperatorDescriptor scanOp = new FileScanOperatorDescriptor(spec, new ConstantFileSplitProvider(inputSplits), stringParser, stringRec);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, scanOp, locations);
    ReplicateOperatorDescriptor replicateOp = new ReplicateOperatorDescriptor(spec, stringRec, outputArity);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, replicateOp, locations);
    IOperatorDescriptor[] outputOp = new IOperatorDescriptor[outputFile.length];
    for (int i = 0; i < outputArity; i++) {
        ResultSetId rsId = new ResultSetId(i);
        spec.addResultSetId(rsId);
        outputOp[i] = new ResultWriterOperatorDescriptor(spec, rsId, true, false, ResultSerializerFactoryProvider.INSTANCE.getResultSerializerFactoryProvider());
        PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, outputOp[i], locations);
    }
    spec.connect(new OneToOneConnectorDescriptor(spec), scanOp, 0, replicateOp, 0);
    for (int i = 0; i < outputArity; i++) {
        spec.connect(new OneToOneConnectorDescriptor(spec), replicateOp, i, outputOp[i], 0);
    }
    for (int i = 0; i < outputArity; i++) {
        spec.addRoot(outputOp[i]);
    }
    String[] expectedResultsFileNames = new String[outputArity];
    for (int i = 0; i < outputArity; i++) {
        expectedResultsFileNames[i] = "data" + File.separator + "device0" + File.separator + inputFileName;
    }
    runTestAndCompareResults(spec, expectedResultsFileNames);
}

Example 40 with DelimitedDataTupleParserFactory

use of org.apache.hyracks.dataflow.std.file.DelimitedDataTupleParserFactory in project asterixdb by apache.

the class ScanPrintTest method scanPrint02.

@Test
public void scanPrint02() throws Exception {
    JobSpecification spec = new JobSpecification();
    FileSplit[] ordersSplits = new FileSplit[] { new ManagedFileSplit(NC2_ID, "data" + File.separator + "tpch0.001" + File.separator + "orders.tbl") };
    IFileSplitProvider ordersSplitsProvider = new ConstantFileSplitProvider(ordersSplits);
    RecordDescriptor ordersDesc = new RecordDescriptor(new ISerializerDeserializer[] { new UTF8StringSerializerDeserializer(), new UTF8StringSerializerDeserializer(), new UTF8StringSerializerDeserializer(), new UTF8StringSerializerDeserializer(), new UTF8StringSerializerDeserializer(), new UTF8StringSerializerDeserializer(), new UTF8StringSerializerDeserializer(), new UTF8StringSerializerDeserializer(), new UTF8StringSerializerDeserializer() });
    FileScanOperatorDescriptor ordScanner = new FileScanOperatorDescriptor(spec, ordersSplitsProvider, new DelimitedDataTupleParserFactory(new IValueParserFactory[] { UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE }, '|'), ordersDesc);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, ordScanner, NC2_ID);
    ResultSetId rsId = new ResultSetId(1);
    IOperatorDescriptor printer = new ResultWriterOperatorDescriptor(spec, rsId, true, false, ResultSerializerFactoryProvider.INSTANCE.getResultSerializerFactoryProvider());
    spec.addResultSetId(rsId);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, printer, NC2_ID);
    IConnectorDescriptor conn1 = new MToNPartitioningConnectorDescriptor(spec, new FieldHashPartitionComputerFactory(new int[] { 0 }, new IBinaryHashFunctionFactory[] { PointableBinaryHashFunctionFactory.of(UTF8StringPointable.FACTORY) }));
    spec.connect(conn1, ordScanner, 0, printer, 0);
    spec.addRoot(printer);
    runTest(spec);
}