Examples with IValueParserFactory org.apache.hyracks.dataflow.common.data.parsers.IValueParserFactory used on opensource projects

Example 6 with IValueParserFactory

use of org.apache.hyracks.dataflow.common.data.parsers.IValueParserFactory in project asterixdb by apache.

the class CountOfCountsTest method countOfCountsExternalSortMultiNC.

@Test
public void countOfCountsExternalSortMultiNC() throws Exception {
    JobSpecification spec = new JobSpecification();
    FileSplit[] splits = new FileSplit[] { new ManagedFileSplit(NC2_ID, "data" + File.separator + "words.txt") };
    IFileSplitProvider splitProvider = new ConstantFileSplitProvider(splits);
    RecordDescriptor desc = new RecordDescriptor(new ISerializerDeserializer[] { new UTF8StringSerializerDeserializer() });
    FileScanOperatorDescriptor csvScanner = new FileScanOperatorDescriptor(spec, splitProvider, new DelimitedDataTupleParserFactory(new IValueParserFactory[] { UTF8StringParserFactory.INSTANCE }, ','), desc);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, csvScanner, NC2_ID);
    ExternalSortOperatorDescriptor sorter = new ExternalSortOperatorDescriptor(spec, 3, new int[] { 0 }, new IBinaryComparatorFactory[] { PointableBinaryComparatorFactory.of(UTF8StringPointable.FACTORY) }, desc);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, sorter, NC1_ID, NC2_ID, NC1_ID, NC2_ID);
    RecordDescriptor desc2 = new RecordDescriptor(new ISerializerDeserializer[] { new UTF8StringSerializerDeserializer(), IntegerSerializerDeserializer.INSTANCE });
    PreclusteredGroupOperatorDescriptor group = new PreclusteredGroupOperatorDescriptor(spec, new int[] { 0 }, new IBinaryComparatorFactory[] { PointableBinaryComparatorFactory.of(UTF8StringPointable.FACTORY) }, new MultiFieldsAggregatorFactory(new IFieldAggregateDescriptorFactory[] { new CountFieldAggregatorFactory(true) }), desc2);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, group, NC1_ID, NC2_ID, NC1_ID, NC2_ID);
    InMemorySortOperatorDescriptor sorter2 = new InMemorySortOperatorDescriptor(spec, new int[] { 1 }, new IBinaryComparatorFactory[] { PointableBinaryComparatorFactory.of(IntegerPointable.FACTORY) }, desc2);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, sorter2, NC1_ID, NC2_ID);
    RecordDescriptor desc3 = new RecordDescriptor(new ISerializerDeserializer[] { IntegerSerializerDeserializer.INSTANCE, IntegerSerializerDeserializer.INSTANCE });
    PreclusteredGroupOperatorDescriptor group2 = new PreclusteredGroupOperatorDescriptor(spec, new int[] { 1 }, new IBinaryComparatorFactory[] { PointableBinaryComparatorFactory.of(IntegerPointable.FACTORY) }, new MultiFieldsAggregatorFactory(new IFieldAggregateDescriptorFactory[] { new CountFieldAggregatorFactory(true) }), desc3);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, group2, NC1_ID, 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, NC1_ID);
    IConnectorDescriptor conn1 = new MToNPartitioningConnectorDescriptor(spec, new FieldHashPartitionComputerFactory(new int[] { 0 }, new IBinaryHashFunctionFactory[] { PointableBinaryHashFunctionFactory.of(UTF8StringPointable.FACTORY) }));
    spec.connect(conn1, csvScanner, 0, sorter, 0);
    IConnectorDescriptor conn2 = new OneToOneConnectorDescriptor(spec);
    spec.connect(conn2, sorter, 0, group, 0);
    IConnectorDescriptor conn3 = new MToNPartitioningConnectorDescriptor(spec, new FieldHashPartitionComputerFactory(new int[] { 1 }, new IBinaryHashFunctionFactory[] { PointableBinaryHashFunctionFactory.of(UTF8StringPointable.FACTORY) }));
    spec.connect(conn3, group, 0, sorter2, 0);
    IConnectorDescriptor conn4 = new OneToOneConnectorDescriptor(spec);
    spec.connect(conn4, sorter2, 0, group2, 0);
    IConnectorDescriptor conn5 = new MToNBroadcastConnectorDescriptor(spec);
    spec.connect(conn5, group2, 0, printer, 0);
    spec.addRoot(printer);
    runTest(spec);
}

Example 7 with IValueParserFactory

use of org.apache.hyracks.dataflow.common.data.parsers.IValueParserFactory in project asterixdb by apache.

the class PushRuntimeTest method scanSelectWrite.

@Test
public void scanSelectWrite() throws Exception {
    JobSpecification spec = new JobSpecification(FRAME_SIZE);
    // the scanner
    FileSplit[] intFileSplits = new FileSplit[1];
    intFileSplits[0] = new ManagedFileSplit(AlgebricksHyracksIntegrationUtil.NC1_ID, "data" + File.separator + "simple" + File.separator + "int-part1.tbl");
    IFileSplitProvider intSplitProvider = new ConstantFileSplitProvider(intFileSplits);
    RecordDescriptor intScannerDesc = new RecordDescriptor(new ISerializerDeserializer[] { IntegerSerializerDeserializer.INSTANCE });
    IValueParserFactory[] valueParsers = new IValueParserFactory[] { IntegerParserFactory.INSTANCE };
    FileScanOperatorDescriptor intScanner = new FileScanOperatorDescriptor(spec, intSplitProvider, new DelimitedDataTupleParserFactory(valueParsers, '|'), intScannerDesc);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, intScanner, DEFAULT_NODES);
    // the algebricks op.
    IScalarEvaluatorFactory cond = new IntegerGreaterThanEvalFactory(new IntegerConstantEvalFactory(2), new TupleFieldEvaluatorFactory(0));
    StreamSelectRuntimeFactory select = new StreamSelectRuntimeFactory(cond, new int[] { 0 }, BinaryBooleanInspectorImpl.FACTORY, false, -1, null);
    RecordDescriptor selectDesc = intScannerDesc;
    String filePath = PATH_ACTUAL + SEPARATOR + "scanSelectWrite.out";
    File outFile = new File(filePath);
    SinkWriterRuntimeFactory writer = new SinkWriterRuntimeFactory(new int[] { 0 }, new IPrinterFactory[] { IntegerPrinterFactory.INSTANCE }, outFile, PrinterBasedWriterFactory.INSTANCE, selectDesc);
    AlgebricksMetaOperatorDescriptor algebricksOp = new AlgebricksMetaOperatorDescriptor(spec, 1, 0, new IPushRuntimeFactory[] { select, writer }, new RecordDescriptor[] { selectDesc, null });
    PartitionConstraintHelper.addPartitionCountConstraint(spec, algebricksOp, 1);
    spec.connect(new OneToOneConnectorDescriptor(spec), intScanner, 0, algebricksOp, 0);
    spec.addRoot(algebricksOp);
    AlgebricksHyracksIntegrationUtil.runJob(spec);
    StringBuilder buf = new StringBuilder();
    readFileToString(outFile, buf);
    Assert.assertEquals("0", buf.toString());
    outFile.delete();
}

Example 8 with IValueParserFactory

use of org.apache.hyracks.dataflow.common.data.parsers.IValueParserFactory in project asterixdb by apache.

the class PushRuntimeTest method scanSplitWrite.

@Test
public void scanSplitWrite() throws Exception {
    final int outputArity = 2;
    JobSpecification spec = new JobSpecification(FRAME_SIZE);
    String[] inputFileName = { "data" + File.separator + "simple" + File.separator + "int-string-part1.tbl", "data" + File.separator + "simple" + File.separator + "int-string-part1-split-0.tbl", "data" + File.separator + "simple" + File.separator + "int-string-part1-split-1.tbl" };
    File[] inputFiles = new File[inputFileName.length];
    for (int i = 0; i < inputFileName.length; i++) {
        inputFiles[i] = new File(inputFileName[i]);
    }
    File[] outputFile = new File[outputArity];
    FileSplit[] outputFileSplit = new FileSplit[outputArity];
    for (int i = 0; i < outputArity; i++) {
        outputFileSplit[i] = createFile(AlgebricksHyracksIntegrationUtil.nc1);
        outputFile[i] = outputFileSplit[i].getFile(AlgebricksHyracksIntegrationUtil.nc1.getIoManager());
    }
    FileSplit[] inputSplits = new FileSplit[] { new ManagedFileSplit(AlgebricksHyracksIntegrationUtil.NC1_ID, inputFileName[0]) };
    IFileSplitProvider intSplitProvider = new ConstantFileSplitProvider(inputSplits);
    RecordDescriptor scannerDesc = new RecordDescriptor(new ISerializerDeserializer[] { IntegerSerializerDeserializer.INSTANCE, new UTF8StringSerializerDeserializer() });
    IValueParserFactory[] valueParsers = new IValueParserFactory[] { IntegerParserFactory.INSTANCE, UTF8StringParserFactory.INSTANCE };
    FileScanOperatorDescriptor intScanner = new FileScanOperatorDescriptor(spec, intSplitProvider, new DelimitedDataTupleParserFactory(valueParsers, '|'), scannerDesc);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, intScanner, DEFAULT_NODES);
    SplitOperatorDescriptor splitOp = new SplitOperatorDescriptor(spec, scannerDesc, outputArity, new TupleFieldEvaluatorFactory(0), BinaryIntegerInspectorImpl.FACTORY);
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, splitOp, new String[] { AlgebricksHyracksIntegrationUtil.NC1_ID });
    IOperatorDescriptor[] outputOp = new IOperatorDescriptor[outputFile.length];
    for (int i = 0; i < outputArity; i++) {
        outputOp[i] = new LineFileWriteOperatorDescriptor(spec, new FileSplit[] { outputFileSplit[i] });
        PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, outputOp[i], new String[] { AlgebricksHyracksIntegrationUtil.NC1_ID });
    }
    spec.connect(new OneToOneConnectorDescriptor(spec), intScanner, 0, splitOp, 0);
    for (int i = 0; i < outputArity; i++) {
        spec.connect(new OneToOneConnectorDescriptor(spec), splitOp, 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[i + 1], outputFile[i].getAbsolutePath());
    }
}

Example 9 with IValueParserFactory

use of org.apache.hyracks.dataflow.common.data.parsers.IValueParserFactory in project asterixdb by apache.

the class PushRuntimeTest method scanLimitWrite.

@Test
public void scanLimitWrite() 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.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, DEFAULT_NODES);
    // the algebricks op.
    StreamLimitRuntimeFactory limit = new StreamLimitRuntimeFactory(new IntegerConstantEvalFactory(2), null, new int[] { 0 }, BinaryIntegerInspectorImpl.FACTORY);
    RecordDescriptor limitDesc = new RecordDescriptor(new ISerializerDeserializer[] { IntegerSerializerDeserializer.INSTANCE });
    String filePath = PATH_ACTUAL + SEPARATOR + "scanLimitWrite.out";
    File outFile = new File(filePath);
    SinkWriterRuntimeFactory writer = new SinkWriterRuntimeFactory(new int[] { 0 }, new IPrinterFactory[] { IntegerPrinterFactory.INSTANCE }, outFile, PrinterBasedWriterFactory.INSTANCE, limitDesc);
    AlgebricksMetaOperatorDescriptor algebricksOp = new AlgebricksMetaOperatorDescriptor(spec, 1, 0, new IPushRuntimeFactory[] { limit, writer }, new RecordDescriptor[] { limitDesc, null });
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, algebricksOp, new String[] { AlgebricksHyracksIntegrationUtil.NC1_ID });
    spec.connect(new OneToOneConnectorDescriptor(spec), scanner, 0, algebricksOp, 0);
    spec.addRoot(algebricksOp);
    AlgebricksHyracksIntegrationUtil.runJob(spec);
    StringBuilder buf = new StringBuilder();
    readFileToString(outFile, buf);
    Assert.assertEquals("12", buf.toString());
    outFile.delete();
}

Example 10 with IValueParserFactory

use of org.apache.hyracks.dataflow.common.data.parsers.IValueParserFactory in project asterixdb by apache.

the class PushRuntimeTest method etsAssignScriptWrite.

@Test
public void etsAssignScriptWrite() throws Exception {
    JobSpecification spec = new JobSpecification(FRAME_SIZE);
    IntegerConstantEvalFactory const1 = new IntegerConstantEvalFactory(400);
    IntegerConstantEvalFactory const2 = new IntegerConstantEvalFactory(3);
    EmptyTupleSourceRuntimeFactory ets = new EmptyTupleSourceRuntimeFactory();
    RecordDescriptor etsDesc = new RecordDescriptor(new ISerializerDeserializer[] {});
    AssignRuntimeFactory assign = new AssignRuntimeFactory(new int[] { 0, 1 }, new IScalarEvaluatorFactory[] { const1, const2 }, new int[] { 0, 1 });
    RecordDescriptor assignDesc = new RecordDescriptor(new ISerializerDeserializer[] { IntegerSerializerDeserializer.INSTANCE, IntegerSerializerDeserializer.INSTANCE });
    IValueParserFactory[] valueParsers = { IntegerParserFactory.INSTANCE, IntegerParserFactory.INSTANCE };
    String osname = System.getProperty("os.name");
    String command;
    if (osname.equals("Linux")) {
        command = "bash target/testscripts/idscript";
    } else if (osname.startsWith("Windows")) {
        command = "target\\testscripts\\idscript.cmd";
    } else {
        // don't know how to test
        return;
    }
    StringStreamingRuntimeFactory script = new StringStreamingRuntimeFactory(command, new IPrinterFactory[] { IntegerPrinterFactory.INSTANCE, IntegerPrinterFactory.INSTANCE }, ' ', new DelimitedDataTupleParserFactory(valueParsers, ' '));
    RecordDescriptor scriptDesc = new RecordDescriptor(new ISerializerDeserializer[] { IntegerSerializerDeserializer.INSTANCE, IntegerSerializerDeserializer.INSTANCE });
    String filePath = PATH_ACTUAL + SEPARATOR + "etsAssignScriptWrite.out";
    File outFile = new File(filePath);
    SinkWriterRuntimeFactory writer = new SinkWriterRuntimeFactory(new int[] { 0, 1 }, new IPrinterFactory[] { IntegerPrinterFactory.INSTANCE, IntegerPrinterFactory.INSTANCE }, outFile, PrinterBasedWriterFactory.INSTANCE, scriptDesc);
    AlgebricksMetaOperatorDescriptor algebricksOp = new AlgebricksMetaOperatorDescriptor(spec, 0, 0, new IPushRuntimeFactory[] { ets, assign, script, writer }, new RecordDescriptor[] { etsDesc, assignDesc, scriptDesc, null });
    PartitionConstraintHelper.addAbsoluteLocationConstraint(spec, algebricksOp, new String[] { AlgebricksHyracksIntegrationUtil.NC1_ID });
    spec.addRoot(algebricksOp);
    AlgebricksHyracksIntegrationUtil.runJob(spec);
    StringBuilder buf = new StringBuilder();
    readFileToString(outFile, buf);
    Assert.assertEquals("400; 3", buf.toString());
    outFile.delete();
}