Java SecondarySort类代码示例

import org.apache.hadoop.examples.SecondarySort; //导入依赖的package包/类
private void runSecondarySort(Configuration conf) throws IOException,
                                                      InterruptedException,
                                                      ClassNotFoundException {
  FileSystem localFs = FileSystem.getLocal(conf);
  localFs.delete(new Path(TEST_ROOT_DIR + "/in"), true);
  localFs.delete(new Path(TEST_ROOT_DIR + "/out"), true);
  TestMapReduceLocal.writeFile
           ("in/part1", "-1 -4\n-3 23\n5 10\n-1 -2\n-1 300\n-1 10\n4 1\n" +
            "4 2\n4 10\n4 -1\n4 -10\n10 20\n10 30\n10 25\n");
  Job job = new Job(conf, "word count");
  job.setJarByClass(WordCount.class);
  job.setNumReduceTasks(2);
  job.setMapperClass(SecondarySort.MapClass.class);
  job.setReducerClass(SecondarySort.Reduce.class);
  // group and partition by the first int in the pair
  job.setPartitionerClass(FirstPartitioner.class);
  job.setGroupingComparatorClass(FirstGroupingComparator.class);

  // the map output is IntPair, IntWritable
  job.setMapOutputKeyClass(IntPair.class);
  job.setMapOutputValueClass(IntWritable.class);

  // the reduce output is Text, IntWritable
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(IntWritable.class);

  FileInputFormat.addInputPath(job, new Path(TEST_ROOT_DIR + "/in"));
  FileOutputFormat.setOutputPath(job, new Path(TEST_ROOT_DIR + "/out"));
  assertTrue(job.waitForCompletion(true));
  String out = TestMapReduceLocal.readFile("out/part-r-00000");
  assertEquals("------------------------------------------------\n" +
               "4\t-10\n4\t-1\n4\t1\n4\t2\n4\t10\n" +
               "------------------------------------------------\n" +
               "10\t20\n10\t25\n10\t30\n", out);
  out = TestMapReduceLocal.readFile("out/part-r-00001");
  assertEquals("------------------------------------------------\n" +
               "-3\t23\n" +
               "------------------------------------------------\n" +
               "-1\t-4\n-1\t-2\n-1\t10\n-1\t300\n" +
               "------------------------------------------------\n" +
               "5\t10\n", out);
}
 

import org.apache.hadoop.examples.SecondarySort; //导入依赖的package包/类
public static void main(String argv[]){
  int exitCode = -1;
  ProgramDriver pgd = new ProgramDriver();
  try {
    pgd.addClass("wordcount", WordCount.class, 
                 "A map/reduce program that counts the words in the input files. multiple input paths supported...");
    
    pgd.addClass("wordmean", WordMean.class,
                 "A map/reduce program that counts the average length of the words in the input files.");
    pgd.addClass("wordmedian", WordMedian.class,
                 "A map/reduce program that counts the median length of the words in the input files.");
    pgd.addClass("wordstandarddeviation", WordStandardDeviation.class,
                 "A map/reduce program that counts the standard deviation of the length of the words in the input files.");
    pgd.addClass("aggregatewordcount", AggregateWordCount.class, 
                 "An Aggregate based map/reduce program that counts the words in the input files.");
    pgd.addClass("aggregatewordhist", AggregateWordHistogram.class, 
                 "An Aggregate based map/reduce program that computes the histogram of the words in the input files.");
    pgd.addClass("grep", Grep.class, 
                 "A map/reduce program that counts the matches of a regex in the input.");
    pgd.addClass("randomwriter", RandomWriter.class, 
                 "A map/reduce program that writes 10GB of random data per node.");
    pgd.addClass("randomtextwriter", RandomTextWriter.class, 
    "A map/reduce program that writes 10GB of random textual data per node.");
    pgd.addClass("sort", Sort.class, "A map/reduce program that sorts the data written by the random writer.");

    pgd.addClass("pi", QuasiMonteCarloModified.class, "Modified pi that accepts a job name, as well as standard <int> <int> args.");
    pgd.addClass("bbp", BaileyBorweinPlouffe.class, BaileyBorweinPlouffe.DESCRIPTION);
    pgd.addClass("distbbp", DistBbp.class, DistBbp.DESCRIPTION);

    pgd.addClass("pentomino", DistributedPentomino.class,
    "A map/reduce tile laying program to find solutions to pentomino problems.");
    pgd.addClass("secondarysort", SecondarySort.class,
                 "An example defining a secondary sort to the reduce.");
    pgd.addClass("sudoku", Sudoku.class, "A sudoku solver.");
    pgd.addClass("join", Join.class, "A job that effects a join over sorted, equally partitioned datasets");
    pgd.addClass("multifilewc", MultiFileWordCount.class, "A job that counts words from several files.");
    pgd.addClass("dbcount", DBCountPageView.class, "An example job that count the pageview counts from a database.");
    pgd.addClass("teragen", TeraGen.class, "Generate data for the terasort");
    pgd.addClass("terasort", TeraSort.class, "Run the terasort");
    pgd.addClass("teravalidate", TeraValidate.class, "Checking results of terasort");
    exitCode = pgd.run(argv);
  }
  catch(Throwable e){
    e.printStackTrace();
  }
  
  System.exit(exitCode);
}
 

import org.apache.hadoop.examples.SecondarySort; //导入依赖的package包/类
private void runSecondarySort(Configuration conf) throws IOException,
                                                      InterruptedException,
                                                      ClassNotFoundException {
  FileSystem localFs = FileSystem.getLocal(conf);
  localFs.delete(new Path(TEST_ROOT_DIR + "/in"), true);
  localFs.delete(new Path(TEST_ROOT_DIR + "/out"), true);
  TestMapReduceLocal.writeFile
           ("in/part1", "-1 -4\n-3 23\n5 10\n-1 -2\n-1 300\n-1 10\n4 1\n" +
            "4 2\n4 10\n4 -1\n4 -10\n10 20\n10 30\n10 25\n");
  Job job = Job.getInstance(conf, "word count");
  job.setJarByClass(WordCount.class);
  job.setNumReduceTasks(2);
  job.setMapperClass(SecondarySort.MapClass.class);
  job.setReducerClass(SecondarySort.Reduce.class);
  // group and partition by the first int in the pair
  job.setPartitionerClass(FirstPartitioner.class);
  job.setGroupingComparatorClass(FirstGroupingComparator.class);

  // the map output is IntPair, IntWritable
  job.setMapOutputKeyClass(IntPair.class);
  job.setMapOutputValueClass(IntWritable.class);

  // the reduce output is Text, IntWritable
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(IntWritable.class);

  FileInputFormat.addInputPath(job, new Path(TEST_ROOT_DIR + "/in"));
  FileOutputFormat.setOutputPath(job, new Path(TEST_ROOT_DIR + "/out"));
  assertTrue(job.waitForCompletion(true));
  String out = TestMapReduceLocal.readFile("out/part-r-00000");
  assertEquals("------------------------------------------------\n" +
               "4\t-10\n4\t-1\n4\t1\n4\t2\n4\t10\n" +
               "------------------------------------------------\n" +
               "10\t20\n10\t25\n10\t30\n", out);
  out = TestMapReduceLocal.readFile("out/part-r-00001");
  assertEquals("------------------------------------------------\n" +
               "-3\t23\n" +
               "------------------------------------------------\n" +
               "-1\t-4\n-1\t-2\n-1\t10\n-1\t300\n" +
               "------------------------------------------------\n" +
               "5\t10\n", out);
}