Java Job.setOutputKeyClass方法代码示例

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();
        conf.setFloat("beta", Float.parseFloat(args[3]));
        Job job = Job.getInstance(conf);
        job.setJarByClass(UnitSum.class);

        ChainMapper.addMapper(job, PassMapper.class, Object.class, Text.class, Text.class, DoubleWritable.class, conf);
        ChainMapper.addMapper(job, BetaMapper.class, Text.class, DoubleWritable.class, Text.class, DoubleWritable.class, conf);

        job.setReducerClass(SumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(DoubleWritable.class);

        MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, PassMapper.class);
        MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class, BetaMapper.class);

        FileOutputFormat.setOutputPath(job, new Path(args[2]));
        job.waitForCompletion(true);
    }
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public int runRandomInputGenerator(int numMappers, long numNodes, Path tmpOutput,
    Integer width, Integer wrapMuplitplier) throws Exception {
  LOG.info("Running RandomInputGenerator with numMappers=" + numMappers
      + ", numNodes=" + numNodes);
  Job job = Job.getInstance(getConf());

  job.setJobName("Random Input Generator");
  job.setNumReduceTasks(0);
  job.setJarByClass(getClass());

  job.setInputFormatClass(GeneratorInputFormat.class);
  job.setOutputKeyClass(BytesWritable.class);
  job.setOutputValueClass(NullWritable.class);

  setJobConf(job, numMappers, numNodes, width, wrapMuplitplier);

  job.setMapperClass(Mapper.class); //identity mapper

  FileOutputFormat.setOutputPath(job, tmpOutput);
  job.setOutputFormatClass(SequenceFileOutputFormat.class);

  boolean success = jobCompletion(job);

  return success ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
/**
 * Creates a simple copy job.
 * 
 * @param conf Configuration object
 * @param outdir Output directory.
 * @param indirs Comma separated input directories.
 * @return Job initialized for a data copy job.
 * @throws Exception If an error occurs creating job configuration.
 */
public static Job createCopyJob(Configuration conf, Path outdir, 
    Path... indirs) throws Exception {
  conf.setInt(MRJobConfig.NUM_MAPS, 3);
  Job theJob = Job.getInstance(conf);
  theJob.setJobName("DataMoveJob");

  FileInputFormat.setInputPaths(theJob, indirs);
  theJob.setMapperClass(DataCopyMapper.class);
  FileOutputFormat.setOutputPath(theJob, outdir);
  theJob.setOutputKeyClass(Text.class);
  theJob.setOutputValueClass(Text.class);
  theJob.setReducerClass(DataCopyReducer.class);
  theJob.setNumReduceTasks(1);
  return theJob;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public int run(String[] args) throws Exception {
  Job job = Job.getInstance(getConf());
  if (args.length != 2) {
    usage();
    return 2;
  }
  TeraInputFormat.setInputPaths(job, new Path(args[0]));
  FileOutputFormat.setOutputPath(job, new Path(args[1]));
  job.setJobName("TeraSum");
  job.setJarByClass(TeraChecksum.class);
  job.setMapperClass(ChecksumMapper.class);
  job.setReducerClass(ChecksumReducer.class);
  job.setOutputKeyClass(NullWritable.class);
  job.setOutputValueClass(Unsigned16.class);
  // force a single reducer
  job.setNumReduceTasks(1);
  job.setInputFormatClass(TeraInputFormat.class);
  return job.waitForCompletion(true) ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
/** {@inheritDoc} */
@Override
public void init(Job job) {
  // setup mapper
  job.setMapperClass(PartitionMapper.class);
  job.setMapOutputKeyClass(IntWritable.class);
  job.setMapOutputValueClass(SummationWritable.class);

  // setup partitioner
  job.setPartitionerClass(IndexPartitioner.class);

  // setup reducer
  job.setReducerClass(SummingReducer.class);
  job.setOutputKeyClass(NullWritable.class);
  job.setOutputValueClass(TaskResult.class);
  final Configuration conf = job.getConfiguration();
  final int nParts = conf.getInt(N_PARTS, 1);
  job.setNumReduceTasks(nParts);

  // setup input
  job.setInputFormatClass(SummationInputFormat.class);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
private Job jobRecommendFriends(String inputPath, String outputPath) throws IOException, InterruptedException, ClassNotFoundException{     
    Job job1 = new Job();
    job1.setJarByClass(WordCount.class);
    job1.setOutputKeyClass(Text.class);
    job1.setOutputValueClass(Text.class);
   
    job1.setMapperClass(MapRecommendation.class);
    job1.setReducerClass(ReduceRecommendation.class);
   
    job1.setOutputFormatClass(TextOutputFormat.class);
    job1.setInputFormatClass(KeyValueTextInputFormat.class);

    FileInputFormat.addInputPath(job1, new Path(inputPath));
    FileOutputFormat.setOutputPath(job1, new Path(outputPath));

    job1.waitForCompletion(true);

    return job1;
   
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {
	Configuration conf = new Configuration();
	
	Job job =Job.getInstance(conf);
	job.setJobName("DocumentFrequencyCount");
	job.setJarByClass(DF.class);
	
	job.setMapOutputKeyClass(Text.class);
	job.setMapOutputValueClass(IntWritable.class);
	
	job.setOutputKeyClass(Text.class);
	job.setOutputValueClass(IntWritable.class);
	
	job.setMapperClass(DFMap.class);
	job.setReducerClass(DFReduce.class);
	
	job.setInputFormatClass(TextInputFormat.class);
	job.setOutputFormatClass(TextOutputFormat.class);
	
	FileInputFormat.addInputPath(job, new Path(args[0]));
	FileOutputFormat.setOutputPath(job, new Path(args[1]));
	boolean wait = job.waitForCompletion(true);
	System.exit(wait ? 0 : 1);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(UnitMultiplication.class);

        ChainMapper.addMapper(job, TransitionMapper.class, Object.class, Text.class, Text.class, Text.class, conf);
        ChainMapper.addMapper(job, PRMapper.class, Object.class, Text.class, Text.class, Text.class, conf);

        job.setReducerClass(MultiplicationReducer.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, TransitionMapper.class);
        MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class, PRMapper.class);

        FileOutputFormat.setOutputPath(job, new Path(args[2]));
        job.waitForCompletion(true);
    }
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
protected Job runFailingMapperJob()
throws IOException, InterruptedException, ClassNotFoundException {
  Configuration myConf = new Configuration(mrCluster.getConfig());
  myConf.setInt(MRJobConfig.NUM_MAPS, 1);
  myConf.setInt(MRJobConfig.MAP_MAX_ATTEMPTS, 2); //reduce the number of attempts

  Job job = Job.getInstance(myConf);

  job.setJarByClass(FailingMapper.class);
  job.setJobName("failmapper");
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(Text.class);
  job.setInputFormatClass(RandomInputFormat.class);
  job.setOutputFormatClass(TextOutputFormat.class);
  job.setMapperClass(FailingMapper.class);
  job.setNumReduceTasks(0);
  
  FileOutputFormat.setOutputPath(job, new Path(OUTPUT_ROOT_DIR,
    "failmapper-output"));
  job.addFileToClassPath(APP_JAR); // The AppMaster jar itself.
  job.submit();
  String trackingUrl = job.getTrackingURL();
  String jobId = job.getJobID().toString();
  boolean succeeded = job.waitForCompletion(true);
  Assert.assertFalse(succeeded);
  Assert.assertTrue("Tracking URL was " + trackingUrl +
                    " but didn't Match Job ID " + jobId ,
        trackingUrl.endsWith(jobId.substring(jobId.lastIndexOf("_")) + "/"));
  return job;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
@Override
public int run(String[] args) throws Exception {
	Configuration conf = this.getConf();
	// 初始化参数
	this.processArgs(conf, args);

	// 创建job
	Job job = Job.getInstance(conf, "active_user");

	// 设置job相关配置参数
	job.setJarByClass(ActiveUserRunner.class);
	// hbase 输入mapper参数
	// 1. 本地运行
	TableMapReduceUtil.initTableMapperJob(this.initScans(job), ActiveUserMapper.class, StatsUserDimension.class,
			TimeOutputValue.class, job, false);
	// 2. 集群运行
	// TableMapReduceUtil.initTableMapperJob(null, ActiveUserMapper.class,
	// StatsUserDimension.class, TimeOutputValue.class, job);

	// 设置reducer相关参数
	job.setReducerClass(ActiveUserReducer.class);
	job.setOutputKeyClass(StatsUserDimension.class);
	job.setOutputValueClass(MapWritableValue.class);

	// 设置output相关参数
	job.setOutputFormatClass(TransformerOutputFormat.class);
	// 开始毫秒数
	long startTime = System.currentTimeMillis();
	try {
		return job.waitForCompletion(true) ? 0 : -1;
	} finally {
		// 结束的毫秒数
		long endTime = System.currentTimeMillis();
		logger.info("Job<" + job.getJobName() + ">是否执行成功:" + job.isSuccessful() + "; 开始时间:" + startTime + "; 结束时间:"
				+ endTime + "; 用时:" + (endTime - startTime) + "ms");
	}
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {
	Configuration conf = new Configuration();
	conf.set("xmlinput.start", "<page>");
	conf.set("xmlinput.end", "</page>");
			
	Job job =Job.getInstance(conf);
	job.setJobName("PageWordCount");
	job.setJarByClass(PageWordCount.class);
	
	job.setOutputKeyClass(Text.class);
	job.setOutputValueClass(IntWritable.class);
	
	job.setMapperClass(PageWordCountMap.class);
	job.setCombinerClass(PageWordCountReduce.class);
	job.setReducerClass(PageWordCountReduce.class);
	
	job.setInputFormatClass(XmlInputFormat.class);
	job.setOutputFormatClass(TextOutputFormat.class);
	
	FileInputFormat.addInputPath(job, new Path(args[0]));
	FileOutputFormat.setOutputPath(job, new Path(args[1]));
	job.waitForCompletion(true);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public int runGenerator(int numMappers, long numNodes, Path tmpOutput,
    Integer width, Integer wrapMuplitplier) throws Exception {
  LOG.info("Running Generator with numMappers=" + numMappers +", numNodes=" + numNodes);
  createSchema();
  Job job = Job.getInstance(getConf());

  job.setJobName("Link Generator");
  job.setNumReduceTasks(0);
  job.setJarByClass(getClass());

  FileInputFormat.setInputPaths(job, tmpOutput);
  job.setInputFormatClass(OneFilePerMapperSFIF.class);
  job.setOutputKeyClass(NullWritable.class);
  job.setOutputValueClass(NullWritable.class);

  setJobConf(job, numMappers, numNodes, width, wrapMuplitplier);

  setMapperForGenerator(job);

  job.setOutputFormatClass(NullOutputFormat.class);

  job.getConfiguration().setBoolean("mapreduce.map.speculative", false);
  TableMapReduceUtil.addDependencyJars(job);
  TableMapReduceUtil.addDependencyJars(job.getConfiguration(), AbstractHBaseTool.class);
  TableMapReduceUtil.initCredentials(job);

  boolean success = jobCompletion(job);

  return success ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static void runJob(Path input, Path output, String vectorClassName,Configuration config)
  throws IOException, InterruptedException, ClassNotFoundException {
  Configuration conf = config;
  conf.set("vector.implementation.class.name", vectorClassName);
  Job job = new Job(conf, "Input Driver running over input: " + input);
	 
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(VectorWritable.class);
  job.setOutputFormatClass(SequenceFileOutputFormat.class);
  job.setMapperClass(InputMapper.class);   
  job.setNumReduceTasks(0);
  job.setJarByClass(InputDriver.class);
  
  FileInputFormat.addInputPath(job, input);
  FileOutputFormat.setOutputPath(job, output);
  
  job.waitForCompletion(true);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
@Override
protected void configureMapper(Job job, String tableName,
    String tableClassName) throws IOException {
  job.setOutputKeyClass(SqoopRecord.class);
  job.setOutputValueClass(NullWritable.class);
  job.setMapperClass(getMapperClass());
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public void testSequenceOutputClassDefaultsToMapRedOutputClass() 
       throws IOException {
  Job job = Job.getInstance();
  // Setting Random class to test getSequenceFileOutput{Key,Value}Class
  job.setOutputKeyClass(FloatWritable.class);
  job.setOutputValueClass(BooleanWritable.class);

  assertEquals("SequenceFileOutputKeyClass should default to ouputKeyClass", 
    FloatWritable.class,
    SequenceFileAsBinaryOutputFormat.getSequenceFileOutputKeyClass(job));
  assertEquals("SequenceFileOutputValueClass should default to " 
    + "ouputValueClass", 
    BooleanWritable.class,
    SequenceFileAsBinaryOutputFormat.getSequenceFileOutputValueClass(job));

  SequenceFileAsBinaryOutputFormat.setSequenceFileOutputKeyClass(job, 
    IntWritable.class );
  SequenceFileAsBinaryOutputFormat.setSequenceFileOutputValueClass(job, 
    DoubleWritable.class ); 

  assertEquals("SequenceFileOutputKeyClass not updated", 
    IntWritable.class,
    SequenceFileAsBinaryOutputFormat.getSequenceFileOutputKeyClass(job));
  assertEquals("SequenceFileOutputValueClass not updated", 
    DoubleWritable.class,
    SequenceFileAsBinaryOutputFormat.getSequenceFileOutputValueClass(job));
}