Search in sources :

Example 26 with NullWritable

use of org.apache.hadoop.io.NullWritable in project jena by apache.

the class CharacteristicSetReducerTest method characteristic_set_reducer_02.

/**
     * Test characteristic set reduction
     * 
     * @throws IOException
     */
@Test
public void characteristic_set_reducer_02() throws IOException {
    MapReduceDriver<CharacteristicSetWritable, CharacteristicSetWritable, CharacteristicSetWritable, CharacteristicSetWritable, CharacteristicSetWritable, NullWritable> driver = this.getMapReduceDriver();
    this.createSet(driver, 2, 1, "http://predicate");
    driver.runTest(false);
    driver = getMapReduceDriver();
    createSet(driver, 2, 1, "http://predicate");
    List<Pair<CharacteristicSetWritable, NullWritable>> results = driver.run();
    CharacteristicSetWritable cw = results.get(0).getFirst();
    Assert.assertEquals(2, cw.getCount().get());
}
Also used : CharacteristicSetWritable(org.apache.jena.hadoop.rdf.types.CharacteristicSetWritable) NullWritable(org.apache.hadoop.io.NullWritable) Pair(org.apache.hadoop.mrunit.types.Pair) Test(org.junit.Test)

Example 27 with NullWritable

use of org.apache.hadoop.io.NullWritable in project jena by apache.

the class TestDistinctTriples method distinct_triples_04.

@Test
public void distinct_triples_04() throws IOException {
    MapReduceDriver<LongWritable, TripleWritable, TripleWritable, NullWritable, NullWritable, TripleWritable> driver = this.getMapReduceDriver();
    Node s1 = NodeFactory.createURI("urn:nf#cbf2b2c7-109e-4097-bbea-f67f272c7fcc");
    Node s2 = NodeFactory.createURI("urn:nf#bb08b75c-1ad2-47ef-acd2-eb2d92b94b89");
    Node p = NodeFactory.createURI("urn:p");
    Node o = NodeFactory.createURI("urn:66.230.159.118");
    Assert.assertNotEquals(s1, s2);
    Triple t1 = new Triple(s1, p, o);
    Triple t2 = new Triple(s2, p, o);
    Assert.assertNotEquals(t1, t2);
    TripleWritable tw1 = new TripleWritable(t1);
    TripleWritable tw2 = new TripleWritable(t2);
    Assert.assertNotEquals(tw1, tw2);
    Assert.assertNotEquals(0, tw1.compareTo(tw2));
    driver.addInput(new LongWritable(1), tw1);
    driver.addInput(new LongWritable(2), tw2);
    driver.addOutput(NullWritable.get(), tw1);
    driver.addOutput(NullWritable.get(), tw2);
    driver.runTest(false);
}
Also used : Triple(org.apache.jena.graph.Triple) TripleWritable(org.apache.jena.hadoop.rdf.types.TripleWritable) Node(org.apache.jena.graph.Node) LongWritable(org.apache.hadoop.io.LongWritable) NullWritable(org.apache.hadoop.io.NullWritable) Test(org.junit.Test)

Example 28 with NullWritable

use of org.apache.hadoop.io.NullWritable in project carbondata by apache.

the class StoreCreator method executeGraph.

/**
   * Execute graph which will further load data
   *
   * @param loadModel
   * @param storeLocation
   * @throws Exception
   */
public static void executeGraph(CarbonLoadModel loadModel, String storeLocation) throws Exception {
    new File(storeLocation).mkdirs();
    String outPutLoc = storeLocation + "/etl";
    String databaseName = loadModel.getDatabaseName();
    String tableName = loadModel.getTableName();
    String tempLocationKey = databaseName + '_' + tableName + "_1";
    CarbonProperties.getInstance().addProperty(tempLocationKey, storeLocation);
    CarbonProperties.getInstance().addProperty("store_output_location", outPutLoc);
    CarbonProperties.getInstance().addProperty("send.signal.load", "false");
    CarbonProperties.getInstance().addProperty("carbon.is.columnar.storage", "true");
    CarbonProperties.getInstance().addProperty("carbon.dimension.split.value.in.columnar", "1");
    CarbonProperties.getInstance().addProperty("carbon.is.fullyfilled.bits", "true");
    CarbonProperties.getInstance().addProperty("is.int.based.indexer", "true");
    CarbonProperties.getInstance().addProperty("aggregate.columnar.keyblock", "true");
    CarbonProperties.getInstance().addProperty("high.cardinality.value", "100000");
    CarbonProperties.getInstance().addProperty("is.compressed.keyblock", "false");
    CarbonProperties.getInstance().addProperty("carbon.leaf.node.size", "120000");
    String graphPath = outPutLoc + File.separator + loadModel.getDatabaseName() + File.separator + tableName + File.separator + 0 + File.separator + 1 + File.separator + tableName + ".ktr";
    File path = new File(graphPath);
    if (path.exists()) {
        path.delete();
    }
    SchemaInfo info = new SchemaInfo();
    BlockDetails blockDetails = new BlockDetails(new Path(loadModel.getFactFilePath()), 0, new File(loadModel.getFactFilePath()).length(), new String[] { "localhost" });
    Configuration configuration = new Configuration();
    CSVInputFormat.setCommentCharacter(configuration, loadModel.getCommentChar());
    CSVInputFormat.setCSVDelimiter(configuration, loadModel.getCsvDelimiter());
    CSVInputFormat.setEscapeCharacter(configuration, loadModel.getEscapeChar());
    CSVInputFormat.setHeaderExtractionEnabled(configuration, true);
    CSVInputFormat.setQuoteCharacter(configuration, loadModel.getQuoteChar());
    CSVInputFormat.setReadBufferSize(configuration, CarbonProperties.getInstance().getProperty(CarbonCommonConstants.CSV_READ_BUFFER_SIZE, CarbonCommonConstants.CSV_READ_BUFFER_SIZE_DEFAULT));
    CSVInputFormat.setMaxColumns(configuration, "10");
    CSVInputFormat.setNumberOfColumns(configuration, "7");
    TaskAttemptContextImpl hadoopAttemptContext = new TaskAttemptContextImpl(configuration, new TaskAttemptID("", 1, TaskType.MAP, 0, 0));
    CSVInputFormat format = new CSVInputFormat();
    RecordReader<NullWritable, StringArrayWritable> recordReader = format.createRecordReader(blockDetails, hadoopAttemptContext);
    CSVRecordReaderIterator readerIterator = new CSVRecordReaderIterator(recordReader, blockDetails, hadoopAttemptContext);
    new DataLoadExecutor().execute(loadModel, storeLocation, new CarbonIterator[] { readerIterator });
    info.setDatabaseName(databaseName);
    info.setTableName(tableName);
    writeLoadMetadata(loadModel.getCarbonDataLoadSchema(), loadModel.getTableName(), loadModel.getTableName(), new ArrayList<LoadMetadataDetails>());
    String segLocation = storeLocation + "/" + databaseName + "/" + tableName + "/Fact/Part0/Segment_0";
    File file = new File(segLocation);
    File factFile = null;
    File[] folderList = file.listFiles();
    File folder = null;
    for (int i = 0; i < folderList.length; i++) {
        if (folderList[i].isDirectory()) {
            folder = folderList[i];
        }
    }
    if (folder.isDirectory()) {
        File[] files = folder.listFiles();
        for (int i = 0; i < files.length; i++) {
            if (!files[i].isDirectory() && files[i].getName().startsWith("part")) {
                factFile = files[i];
                break;
            }
        }
        factFile.renameTo(new File(segLocation + "/" + factFile.getName()));
        CarbonUtil.deleteFoldersAndFiles(folder);
    }
}
Also used : Path(org.apache.hadoop.fs.Path) CarbonTablePath(org.apache.carbondata.core.util.path.CarbonTablePath) CarbonStorePath(org.apache.carbondata.core.util.path.CarbonStorePath) Configuration(org.apache.hadoop.conf.Configuration) TaskAttemptID(org.apache.hadoop.mapred.TaskAttemptID) LoadMetadataDetails(org.apache.carbondata.core.statusmanager.LoadMetadataDetails) CSVRecordReaderIterator(org.apache.carbondata.processing.csvload.CSVRecordReaderIterator) StringArrayWritable(org.apache.carbondata.processing.csvload.StringArrayWritable) NullWritable(org.apache.hadoop.io.NullWritable) CSVInputFormat(org.apache.carbondata.processing.csvload.CSVInputFormat) BlockDetails(org.apache.carbondata.processing.csvload.BlockDetails) TaskAttemptContextImpl(org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl) File(java.io.File) DataLoadExecutor(org.apache.carbondata.processing.newflow.DataLoadExecutor) SchemaInfo(org.apache.carbondata.processing.api.dataloader.SchemaInfo)

Example 29 with NullWritable

use of org.apache.hadoop.io.NullWritable in project camel by apache.

the class HdfsConsumerTest method testReadBoolean.

@Test
public void testReadBoolean() throws Exception {
    if (!canTest()) {
        return;
    }
    final Path file = new Path(new File("target/test/test-camel-boolean").getAbsolutePath());
    Configuration conf = new Configuration();
    FileSystem fs1 = FileSystem.get(file.toUri(), conf);
    SequenceFile.Writer writer = createWriter(fs1, conf, file, NullWritable.class, BooleanWritable.class);
    NullWritable keyWritable = NullWritable.get();
    BooleanWritable valueWritable = new BooleanWritable();
    valueWritable.set(true);
    writer.append(keyWritable, valueWritable);
    writer.sync();
    writer.close();
    context.addRoutes(new RouteBuilder() {

        public void configure() {
            from("hdfs:localhost/" + file.toUri() + "?fileSystemType=LOCAL&fileType=SEQUENCE_FILE&initialDelay=0").to("mock:result");
        }
    });
    context.start();
    MockEndpoint resultEndpoint = context.getEndpoint("mock:result", MockEndpoint.class);
    resultEndpoint.expectedMessageCount(1);
    resultEndpoint.assertIsSatisfied();
}
Also used : Path(org.apache.hadoop.fs.Path) Configuration(org.apache.hadoop.conf.Configuration) SequenceFile(org.apache.hadoop.io.SequenceFile) RouteBuilder(org.apache.camel.builder.RouteBuilder) BooleanWritable(org.apache.hadoop.io.BooleanWritable) MockEndpoint(org.apache.camel.component.mock.MockEndpoint) FileSystem(org.apache.hadoop.fs.FileSystem) ArrayFile(org.apache.hadoop.io.ArrayFile) SequenceFile(org.apache.hadoop.io.SequenceFile) File(java.io.File) NullWritable(org.apache.hadoop.io.NullWritable) Test(org.junit.Test)

Example 30 with NullWritable

use of org.apache.hadoop.io.NullWritable in project camel by apache.

the class HdfsConsumerTest method testReadInt.

@Test
public void testReadInt() throws Exception {
    if (!canTest()) {
        return;
    }
    final Path file = new Path(new File("target/test/test-camel-int").getAbsolutePath());
    Configuration conf = new Configuration();
    FileSystem fs1 = FileSystem.get(file.toUri(), conf);
    SequenceFile.Writer writer = createWriter(fs1, conf, file, NullWritable.class, IntWritable.class);
    NullWritable keyWritable = NullWritable.get();
    IntWritable valueWritable = new IntWritable();
    int value = 314159265;
    valueWritable.set(value);
    writer.append(keyWritable, valueWritable);
    writer.sync();
    writer.close();
    MockEndpoint resultEndpoint = context.getEndpoint("mock:result", MockEndpoint.class);
    resultEndpoint.expectedMessageCount(1);
    context.addRoutes(new RouteBuilder() {

        public void configure() {
            from("hdfs:localhost/" + file.toUri() + "?fileSystemType=LOCAL&fileType=SEQUENCE_FILE&initialDelay=0").to("mock:result");
        }
    });
    context.start();
    resultEndpoint.assertIsSatisfied();
}
Also used : Path(org.apache.hadoop.fs.Path) Configuration(org.apache.hadoop.conf.Configuration) SequenceFile(org.apache.hadoop.io.SequenceFile) RouteBuilder(org.apache.camel.builder.RouteBuilder) MockEndpoint(org.apache.camel.component.mock.MockEndpoint) FileSystem(org.apache.hadoop.fs.FileSystem) ArrayFile(org.apache.hadoop.io.ArrayFile) SequenceFile(org.apache.hadoop.io.SequenceFile) File(java.io.File) NullWritable(org.apache.hadoop.io.NullWritable) IntWritable(org.apache.hadoop.io.IntWritable) MockEndpoint(org.apache.camel.component.mock.MockEndpoint) Test(org.junit.Test)

Aggregations

NullWritable (org.apache.hadoop.io.NullWritable)113 Test (org.junit.Test)68 Path (org.apache.hadoop.fs.Path)47 Configuration (org.apache.hadoop.conf.Configuration)44 File (java.io.File)33 FileSystem (org.apache.hadoop.fs.FileSystem)28 SequenceFile (org.apache.hadoop.io.SequenceFile)24 JobConf (org.apache.hadoop.mapred.JobConf)24 RouteBuilder (org.apache.camel.builder.RouteBuilder)18 MockEndpoint (org.apache.camel.component.mock.MockEndpoint)18 ArrayFile (org.apache.hadoop.io.ArrayFile)18 Text (org.apache.hadoop.io.Text)17 InputSplit (org.apache.hadoop.mapred.InputSplit)17 LongWritable (org.apache.hadoop.io.LongWritable)16 IntWritable (org.apache.hadoop.io.IntWritable)11 IOException (java.io.IOException)10 Writer (org.apache.hadoop.io.SequenceFile.Writer)9 TaskAttemptContextImpl (org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl)8 Pair (org.apache.hadoop.mrunit.types.Pair)8 CharacteristicSetWritable (org.apache.jena.hadoop.rdf.types.CharacteristicSetWritable)8