Java OutputFormat类代码示例

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
/**
   * Adds a named output for the job.
   * <p/>
   *
   * @param job               job to add the named output
   * @param namedOutput       named output name, it has to be a word, letters
   *                          and numbers only, cannot be the word 'part' as
   *                          that is reserved for the default output.
   * @param outputFormatClass OutputFormat class.
   * @param keySchema          Schema for the Key
   * @param valueSchema        Schema for the Value (used in case of AvroKeyValueOutputFormat or null)
   */
  @SuppressWarnings("rawtypes")
public static void addNamedOutput(Job job, String namedOutput,
      Class<? extends OutputFormat> outputFormatClass,
      Schema keySchema, Schema valueSchema) {
    checkNamedOutputName(job, namedOutput, true);
    Configuration conf = job.getConfiguration();
    conf.set(MULTIPLE_OUTPUTS,
      conf.get(MULTIPLE_OUTPUTS, "") + " " + namedOutput);
    conf.setClass(MO_PREFIX + namedOutput + FORMAT, outputFormatClass,
      OutputFormat.class);
    conf.set(MO_PREFIX+namedOutput+".keyschema", keySchema.toString());
    if(valueSchema!=null){
      conf.set(MO_PREFIX+namedOutput+".valueschema",valueSchema.toString());
    }
  }
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
@Override
public void updateTable(ExportJobContext context) throws IOException,
    ExportException {

  logExportTableDetails(context);

  context.setConnManager(this);

  @SuppressWarnings("rawtypes")
  Class<? extends OutputFormat> oraOopOutputFormatClass;
  try {
    oraOopOutputFormatClass = OraOopOutputFormatUpdate.class;
  } catch (NoClassDefFoundError ex) {
    explainWhyExportClassCannotBeLoaded(ex, "OraOopOutputFormatUpdate");
    throw ex;
  }

  JdbcUpdateExportJob exportJob =
      new JdbcUpdateExportJob(context, null, null, oraOopOutputFormatClass);
  exportJob.runExport();
}
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
@Override
protected Class<? extends OutputFormat> getOutputFormatClass()
    throws ClassNotFoundException {
  if (isHCatJob) {
    LOG.debug("Returning HCatOutputFormat for output format");
    return SqoopHCatUtilities.getOutputFormatClass();
  }
  if (options.getFileLayout() == SqoopOptions.FileLayout.TextFile) {
    return RawKeyTextOutputFormat.class;
  } else if (options.getFileLayout()
      == SqoopOptions.FileLayout.SequenceFile) {
    return SequenceFileOutputFormat.class;
  } else if (options.getFileLayout()
      == SqoopOptions.FileLayout.AvroDataFile) {
    return AvroOutputFormat.class;
  } else if (options.getFileLayout()
      == SqoopOptions.FileLayout.ParquetFile) {
    return DatasetKeyOutputFormat.class;
  }

  return null;
}
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
private void writeBadOutput(TaskAttempt attempt, Configuration conf)
  throws Exception {
  TaskAttemptContext tContext = new TaskAttemptContextImpl(conf, 
      TypeConverter.fromYarn(attempt.getID()));
 
  TextOutputFormat<?, ?> theOutputFormat = new TextOutputFormat();
  RecordWriter theRecordWriter = theOutputFormat
      .getRecordWriter(tContext);
  
  NullWritable nullWritable = NullWritable.get();
  try {
    theRecordWriter.write(key2, val2);
    theRecordWriter.write(null, nullWritable);
    theRecordWriter.write(null, val2);
    theRecordWriter.write(nullWritable, val1);
    theRecordWriter.write(key1, nullWritable);
    theRecordWriter.write(key2, null);
    theRecordWriter.write(null, null);
    theRecordWriter.write(key1, val1);
  } finally {
    theRecordWriter.close(tContext);
  }
  
  OutputFormat outputFormat = ReflectionUtils.newInstance(
      tContext.getOutputFormatClass(), conf);
  OutputCommitter committer = outputFormat.getOutputCommitter(tContext);
  committer.commitTask(tContext);
}
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
private void writeOutput(TaskAttempt attempt, Configuration conf)
  throws Exception {
  TaskAttemptContext tContext = new TaskAttemptContextImpl(conf, 
      TypeConverter.fromYarn(attempt.getID()));
  
  TextOutputFormat<?, ?> theOutputFormat = new TextOutputFormat();
  RecordWriter theRecordWriter = theOutputFormat
      .getRecordWriter(tContext);
  
  NullWritable nullWritable = NullWritable.get();
  try {
    theRecordWriter.write(key1, val1);
    theRecordWriter.write(null, nullWritable);
    theRecordWriter.write(null, val1);
    theRecordWriter.write(nullWritable, val2);
    theRecordWriter.write(key2, nullWritable);
    theRecordWriter.write(key1, null);
    theRecordWriter.write(null, null);
    theRecordWriter.write(key2, val2);
  } finally {
    theRecordWriter.close(tContext);
  }
  
  OutputFormat outputFormat = ReflectionUtils.newInstance(
      tContext.getOutputFormatClass(), conf);
  OutputCommitter committer = outputFormat.getOutputCommitter(tContext);
  committer.commitTask(tContext);
}
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
private void testSuccessfulJob(String filename,
    Class<? extends OutputFormat> output, String[] exclude) throws Exception {
  Path outDir = getNewOutputDir();
  Job job = MapReduceTestUtil.createJob(conf, inDir, outDir, 1, 0);
  job.setOutputFormatClass(output);

  assertTrue("Job failed!", job.waitForCompletion(true));

  Path testFile = new Path(outDir, filename);
  assertTrue("Done file missing for job " + job.getJobID(), fs.exists(testFile));

  // check if the files from the missing set exists
  for (String ex : exclude) {
    Path file = new Path(outDir, ex);
    assertFalse("File " + file + " should not be present for successful job "
        + job.getJobID(), fs.exists(file));
  }
}
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
private void testFailedJob(String fileName,
    Class<? extends OutputFormat> output, String[] exclude) throws Exception {
  Path outDir = getNewOutputDir();
  Job job = MapReduceTestUtil.createFailJob(conf, outDir, inDir);
  job.setOutputFormatClass(output);

  assertFalse("Job did not fail!", job.waitForCompletion(true));

  if (fileName != null) {
    Path testFile = new Path(outDir, fileName);
    assertTrue("File " + testFile + " missing for failed job " + job.getJobID(),
        fs.exists(testFile));
  }

  // check if the files from the missing set exists
  for (String ex : exclude) {
    Path file = new Path(outDir, ex);
    assertFalse("File " + file + " should not be present for failed job "
        + job.getJobID(), fs.exists(file));
  }
}
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
private org.apache.hadoop.mapreduce.OutputCommitter 
createOutputCommitter(boolean newApiCommitter, JobID jobId, Configuration conf) throws Exception {
  org.apache.hadoop.mapreduce.OutputCommitter committer = null;

  LOG.info("OutputCommitter set in config "
      + conf.get("mapred.output.committer.class"));

  if (newApiCommitter) {
    org.apache.hadoop.mapreduce.TaskID taskId =
        new org.apache.hadoop.mapreduce.TaskID(jobId, TaskType.MAP, 0);
    org.apache.hadoop.mapreduce.TaskAttemptID taskAttemptID =
        new org.apache.hadoop.mapreduce.TaskAttemptID(taskId, 0);
    org.apache.hadoop.mapreduce.TaskAttemptContext taskContext = 
        new TaskAttemptContextImpl(conf, taskAttemptID);
    OutputFormat outputFormat =
      ReflectionUtils.newInstance(taskContext.getOutputFormatClass(), conf);
    committer = outputFormat.getOutputCommitter(taskContext);
  } else {
    committer = ReflectionUtils.newInstance(conf.getClass(
        "mapred.output.committer.class", FileOutputCommitter.class,
        org.apache.hadoop.mapred.OutputCommitter.class), conf);
  }
  LOG.info("OutputCommitter is " + committer.getClass().getName());
  return committer;
}
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
MapRunner() throws IOException, InterruptedException, 
     ClassNotFoundException {
         // initiate the real mapper that does the work
         mapper = ReflectionUtils.newInstance(mapClass,
             outer.getConfiguration());
         @SuppressWarnings("unchecked")
OutputFormat<K2, V2> outputFormat = (OutputFormat<K2, V2>) 
    ReflectionUtils.newInstance(outer.getOutputFormatClass(),
             outer.getConfiguration());
         try {
             // outputFormat is not initialized.  Relying on everything it 
             // needs can be obtained from the AssignmentManager singleton.
             writer = outputFormat.getRecordWriter(outer);
             subcontext = (Context)ReflectionUtil.createMapperContext(
                 mapper, outer.getConfiguration(), outer.getTaskAttemptID(),                 
                 new SubMapRecordReader(), writer,
                 outer.getOutputCommitter(), new SubMapStatusReporter(),
                 outer.getInputSplit());
         } catch (Exception e) {
             throw new IOException("Error creating mapper context", e);
         }
     }
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
public LocalMapTask(InputFormat<INKEY, INVALUE> inputFormat, 
             OutputFormat<OUTKEY, OUTVALUE> outputFormat, 
             Configuration conf, int id, InputSplit split, 
             ContentPumpReporter reporter, AtomicInteger pctProgress) {
         this.inputFormat = inputFormat;
         this.outputFormat = outputFormat;
         this.conf = conf;
         this.id = id;
         this.split = split;
         this.pctProgress = pctProgress;
         this.reporter = reporter;
         try {
	mapperClass = job.getMapperClass();
} catch (ClassNotFoundException e) {
	LOG.error("Mapper class not found", e);
}
     }
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
@Test(enabled = true)
public void testWriteBufferData() throws Exception {
  NullWritable nada = NullWritable.get();
  MneDurableOutputSession<DurableBuffer<?>> sess =
      new MneDurableOutputSession<DurableBuffer<?>>(m_tacontext, null,
          MneConfigHelper.DEFAULT_OUTPUT_CONFIG_PREFIX);
  MneDurableOutputValue<DurableBuffer<?>> mdvalue =
      new MneDurableOutputValue<DurableBuffer<?>>(sess);
  OutputFormat<NullWritable, MneDurableOutputValue<DurableBuffer<?>>> outputFormat =
      new MneOutputFormat<MneDurableOutputValue<DurableBuffer<?>>>();
  RecordWriter<NullWritable, MneDurableOutputValue<DurableBuffer<?>>> writer =
      outputFormat.getRecordWriter(m_tacontext);
  DurableBuffer<?> dbuf = null;
  Checksum cs = new CRC32();
  cs.reset();
  for (int i = 0; i < m_reccnt; ++i) {
    dbuf = genupdDurableBuffer(sess, cs);
    Assert.assertNotNull(dbuf);
    writer.write(nada, mdvalue.of(dbuf));
  }
  m_checksum = cs.getValue();
  writer.close(m_tacontext);
  sess.close();
}
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
@Test(enabled = true)
public void testWriteChunkData() throws Exception {
  NullWritable nada = NullWritable.get();
  MneDurableOutputSession<DurableChunk<?>> sess =
      new MneDurableOutputSession<DurableChunk<?>>(m_tacontext, null,
          MneConfigHelper.DEFAULT_OUTPUT_CONFIG_PREFIX);
  MneDurableOutputValue<DurableChunk<?>> mdvalue =
      new MneDurableOutputValue<DurableChunk<?>>(sess);
  OutputFormat<NullWritable, MneDurableOutputValue<DurableChunk<?>>> outputFormat =
      new MneOutputFormat<MneDurableOutputValue<DurableChunk<?>>>();
  RecordWriter<NullWritable, MneDurableOutputValue<DurableChunk<?>>> writer =
      outputFormat.getRecordWriter(m_tacontext);
  DurableChunk<?> dchunk = null;
  Checksum cs = new CRC32();
  cs.reset();
  for (int i = 0; i < m_reccnt; ++i) {
    dchunk = genupdDurableChunk(sess, cs);
    Assert.assertNotNull(dchunk);
    writer.write(nada, mdvalue.of(dchunk));
  }
  m_checksum = cs.getValue();
  writer.close(m_tacontext);
  sess.close();
}
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
@Test(enabled = true)
public void testWritePersonData() throws Exception {
  NullWritable nada = NullWritable.get();
  MneDurableOutputSession<Person<Long>> sess =
      new MneDurableOutputSession<Person<Long>>(m_tacontext, null,
          MneConfigHelper.DEFAULT_OUTPUT_CONFIG_PREFIX);
  MneDurableOutputValue<Person<Long>> mdvalue =
      new MneDurableOutputValue<Person<Long>>(sess);
  OutputFormat<NullWritable, MneDurableOutputValue<Person<Long>>> outputFormat =
      new MneOutputFormat<MneDurableOutputValue<Person<Long>>>();
  RecordWriter<NullWritable, MneDurableOutputValue<Person<Long>>> writer =
      outputFormat.getRecordWriter(m_tacontext);
  Person<Long> person = null;
  for (int i = 0; i < m_reccnt; ++i) {
    person = sess.newDurableObjectRecord();
    person.setAge((short) m_rand.nextInt(50));
    person.setName(String.format("Name: [%s]", Utils.genRandomString()), true);
    m_sumage += person.getAge();
    writer.write(nada, mdvalue.of(person));
  }
  writer.close(m_tacontext);
  sess.close();
}
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
@Test(enabled = true)
public void testWriteLongData() throws Exception {
  NullWritable nada = NullWritable.get();
  MneDurableOutputSession<Long> sess =
      new MneDurableOutputSession<Long>(m_tacontext, null,
          MneConfigHelper.DEFAULT_OUTPUT_CONFIG_PREFIX);
  MneDurableOutputValue<Long> mdvalue =
      new MneDurableOutputValue<Long>(sess);
  OutputFormat<NullWritable, MneDurableOutputValue<Long>> outputFormat =
      new MneOutputFormat<MneDurableOutputValue<Long>>();
  RecordWriter<NullWritable, MneDurableOutputValue<Long>> writer =
      outputFormat.getRecordWriter(m_tacontext);
  Long val = null;
  for (int i = 0; i < m_reccnt; ++i) {
    val = m_rand.nextLong();
    m_sum += val;
    writer.write(nada, mdvalue.of(val));
  }
  writer.close(m_tacontext);
  sess.close();
}
 

import org.apache.hadoop.mapreduce.OutputFormat; //导入依赖的package包/类
@Test
public void testBasicMultiSave() throws Exception {
    JobConf conf = createJobConf();
    conf.set(ConfigurationOptions.ES_RESOURCE, "oldapi/multi-save");

    MultiOutputFormat.addOutputFormat(conf, EsOutputFormat.class);
    MultiOutputFormat.addOutputFormat(conf, PrintStreamOutputFormat.class);
    //MultiOutputFormat.addOutputFormat(conf, TextOutputFormat.class);

    PrintStreamOutputFormat.stream(conf, Stream.OUT);
    //conf.set("mapred.output.dir", "foo/bar");
    //FileOutputFormat.setOutputPath(conf, new Path("foo/bar"));

    conf.setClass("mapred.output.format.class", MultiOutputFormat.class, OutputFormat.class);
    runJob(conf);
}