Java Code Examples for org.apache.crunch.PCollection#parallelDo()

public static <T extends SpecificRecord> PCollection<ThriftRecord> byFieldNames(
    final PCollection<T> collection,
    final String rowKeyFieldName,
    final String ttlFieldName,
    final String timestampFieldName
) {
  final Class<T> recordType = collection.getPType().getTypeClass();
  T record;
  try {
    record = recordType.getConstructor().newInstance();
  } catch (Exception e) {
    throw new RuntimeException("Could not create an instance of the record to determine it's schema", e);
  }

  ThriftByFieldNamesFn<T> doFn = new ThriftByFieldNamesFn<T>(record.getSchema(), rowKeyFieldName, ttlFieldName, timestampFieldName);
  return collection.parallelDo(doFn, ThriftRecord.PTYPE);
}
 

public int run(String[] args) throws Exception {

    String fooInputPath = args[0];
    String barInputPath = args[1];
    String outputPath = args[2];
    int fooValMax = Integer.parseInt(args[3]);
    int joinValMax = Integer.parseInt(args[4]);
    int numberOfReducers = Integer.parseInt(args[5]);

    Pipeline pipeline = new MRPipeline(JoinFilterExampleCrunch.class, getConf()); //<1>
    
    PCollection<String> fooLines = pipeline.readTextFile(fooInputPath);  //<2>
    PCollection<String> barLines = pipeline.readTextFile(barInputPath);

    PTable<Long, Pair<Long, Integer>> fooTable = fooLines.parallelDo(  //<3>
        new FooIndicatorFn(),
        Avros.tableOf(Avros.longs(),
        Avros.pairs(Avros.longs(), Avros.ints())));

    fooTable = fooTable.filter(new FooFilter(fooValMax));  //<4>

    PTable<Long, Integer> barTable = barLines.parallelDo(new BarIndicatorFn(),
        Avros.tableOf(Avros.longs(), Avros.ints()));

    DefaultJoinStrategy<Long, Pair<Long, Integer>, Integer> joinStrategy =   //<5>
        new DefaultJoinStrategy
          <Long, Pair<Long, Integer>, Integer>
          (numberOfReducers);

    PTable<Long, Pair<Pair<Long, Integer>, Integer>> joinedTable = joinStrategy //<6>
        .join(fooTable, barTable, JoinType.INNER_JOIN);

    PTable<Long, Pair<Pair<Long, Integer>, Integer>> filteredTable = joinedTable.filter(new JoinFilter(joinValMax));

    filteredTable.write(At.textFile(outputPath), WriteMode.OVERWRITE); //<7>

    PipelineResult result = pipeline.done();

    return result.succeeded() ? 0 : 1;
  }
 

public int run(String[] args) throws Exception {

        if (args.length != 2) {
            System.err.println("Usage: hadoop jar crunch-1.0.0-SNAPSHOT-job.jar" + " [generic options] input output");
            System.err.println();
            GenericOptionsParser.printGenericCommandUsage(System.err);
            return 1;
        }

        String inputPath = args[0];
        String outputPath = args[1];

        // Create an object to coordinate pipeline creation and execution.
        Pipeline pipeline = new MRPipeline(WordCount.class, getConf());

        // Reference a given text file as a collection of Strings.
        PCollection<String> lines = pipeline.readTextFile(inputPath);

        // Define a function that splits each line in a PCollection of Strings into
        // a PCollection made up of the individual words in the file.
        // The second argument sets the serialization format.
        PCollection<String> words = lines.parallelDo(new Tokenizer(), Writables.strings());

        // Take the collection of words and remove known stop words.
        PCollection<String> noStopWords = words.filter(new StopWordFilter());

        // The count method applies a series of Crunch primitives and returns
        // a map of the unique words in the input PCollection to their counts.
        PTable<String, Long> counts = noStopWords.count();

        // Instruct the pipeline to write the resulting counts to a text file.
        pipeline.writeTextFile(counts, outputPath);

        // Execute the pipeline as a MapReduce.
        PipelineResult result = pipeline.done();

        return result.succeeded() ? 0 : 1;
    }
 

@Test
public void whenFunctionCalled_counterIncementendForChangedValues() {
    PCollection<String> inputStrings = MemPipeline.collectionOf("This", "is", "a", "TEST", "string");
    PCollection<String> upperCaseStrings = inputStrings.parallelDo(new ToUpperCaseWithCounterFn(), Writables.strings());

    assertEquals(ImmutableList.of("THIS", "IS", "A", "TEST", "STRING"), Lists.newArrayList(upperCaseStrings.materialize()));
    assertEquals(4L, MemPipeline.getCounters()
        .findCounter("UpperCase", "modified")
        .getValue());
}
 

private static <E> PCollection<E> partition(PCollection<E> collection,
                                            int numReducers) {
  PType<E> type = collection.getPType();
  PTableType<E, Void> tableType = Avros.tableOf(type, Avros.nulls());
  PTable<E, Void> table = collection.parallelDo(new AsKeyTable<E>(), tableType);
  PGroupedTable<E, Void> grouped =
      numReducers > 0 ? table.groupByKey(numReducers) : table.groupByKey();
  return grouped.ungroup().keys();
}
 

@Test
public void testUseReaderSchema() throws IOException {

  // Create a schema with only a username, so we can test reading it
  // with an enhanced record structure.
  Schema oldRecordSchema = SchemaBuilder.record("org.kitesdk.data.user.OldUserRecord")
      .fields()
      .requiredString("username")
      .endRecord();

  // create the dataset
  Dataset<Record> in = repo.create("ns", "in", new DatasetDescriptor.Builder()
      .schema(oldRecordSchema).build());
  Dataset<Record> out = repo.create("ns", "out", new DatasetDescriptor.Builder()
      .schema(oldRecordSchema).build());
  Record oldUser = new Record(oldRecordSchema);
  oldUser.put("username", "user");

  DatasetWriter<Record> writer = in.newWriter();

  try {

    writer.write(oldUser);

  } finally {
    writer.close();
  }

  Pipeline pipeline = new MRPipeline(TestCrunchDatasets.class);

  // read data from updated dataset that has the new schema.
  // At this point, User class has the old schema
  PCollection<NewUserRecord> data = pipeline.read(CrunchDatasets.asSource(in.getUri(),
      NewUserRecord.class));

  PCollection<NewUserRecord> processed = data.parallelDo(new UserRecordIdentityFn(),
      Avros.records(NewUserRecord.class));

  pipeline.write(processed, CrunchDatasets.asTarget(out));

  DatasetReader reader = out.newReader();

  Assert.assertTrue("Pipeline failed.", pipeline.run().succeeded());

  try {

    // there should be one record that is equal to our old user generic record.
    Assert.assertEquals(oldUser, reader.next());
    Assert.assertFalse(reader.hasNext());

  } finally {
    reader.close();
  }
}
 

@Test
public void testUseReaderSchemaParquet() throws IOException {

  // Create a schema with only a username, so we can test reading it
  // with an enhanced record structure.
  Schema oldRecordSchema = SchemaBuilder.record("org.kitesdk.data.user.OldUserRecord")
      .fields()
      .requiredString("username")
      .endRecord();

  // create the dataset
  Dataset<Record> in = repo.create("ns", "in", new DatasetDescriptor.Builder()
      .format(Formats.PARQUET).schema(oldRecordSchema).build());

  Dataset<Record> out = repo.create("ns", "out", new DatasetDescriptor.Builder()
      .format(Formats.PARQUET).schema(oldRecordSchema).build());
  Record oldUser = new Record(oldRecordSchema);
  oldUser.put("username", "user");

  DatasetWriter<Record> writer = in.newWriter();

  try {

    writer.write(oldUser);

  } finally {
    writer.close();
  }

  Pipeline pipeline = new MRPipeline(TestCrunchDatasets.class);

  // read data from updated dataset that has the new schema.
  // At this point, User class has the old schema
  PCollection<NewUserRecord> data = pipeline.read(CrunchDatasets.asSource(in.getUri(),
      NewUserRecord.class));

  PCollection<NewUserRecord> processed = data.parallelDo(new UserRecordIdentityFn(),
      Avros.records(NewUserRecord.class));

  pipeline.write(processed, CrunchDatasets.asTarget(out));

  DatasetReader reader = out.newReader();

  Assert.assertTrue("Pipeline failed.", pipeline.run().succeeded());

  try {

    // there should be one record that is equal to our old user generic record.
    Assert.assertEquals(oldUser, reader.next());
    Assert.assertFalse(reader.hasNext());

  } finally {
    reader.close();
  }
}