How to use

aggregate

method

in

org.apache.crunch.PCollection

public int run(String[] args) throws Exception {
 if (args.length != 1) {
  System.err.println();
  System.err.println("Usage: " + this.getClass().getName() + " [generic options] input");
  System.err.println();
  GenericOptionsParser.printGenericCommandUsage(System.err);
  return 1;
 }
 // Create an object to coordinate pipeline creation and execution.
 Pipeline pipeline = new MRPipeline(TotalWordCount.class, getConf());
 // Reference a given text file as a collection of Strings.
 PCollection<String> lines = pipeline.readTextFile(args[0]);
 // Define a function that splits each line in a PCollection of Strings into
 // a
 // PCollection made up of the individual words in the file.
 PCollection<Long> numberOfWords = lines.parallelDo(new DoFn<String, Long>() {
  public void process(String line, Emitter<Long> emitter) {
   emitter.emit((long)line.split("\\s+").length);
  }
 }, Writables.longs()); // Indicates the serialization format
 // The aggregate method groups a collection into a single PObject.
 PObject<Long> totalCount = numberOfWords.aggregate(Aggregators.SUM_LONGS()).first();
 // Execute the pipeline as a MapReduce.
 PipelineResult result = pipeline.run();
 System.out.println("Total number of words: " + totalCount.getValue());
 
 pipeline.done();
 return result.succeeded() ? 0 : 1;
}