Java SequenceFileRecordReader类代码示例

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
/**
 * Actually instantiate the user's chosen RecordReader implementation.
 */
@SuppressWarnings("unchecked")
private void createChildReader() throws IOException, InterruptedException {
  LOG.debug("ChildSplit operates on: " + split.getPath(index));

  Configuration conf = context.getConfiguration();

  // Determine the file format we're reading.
  Class rrClass;
  if (ExportJobBase.isSequenceFiles(conf, split.getPath(index))) {
    rrClass = SequenceFileRecordReader.class;
  } else {
    rrClass = LineRecordReader.class;
  }

  // Create the appropriate record reader.
  this.rr = (RecordReader<LongWritable, Object>)
      ReflectionUtils.newInstance(rrClass, conf);
}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
@SuppressWarnings("unchecked")
@Override
public void initialize(InputSplit curSplit, TaskAttemptContext curContext) throws IOException, InterruptedException {
	this.split = (CombineFileSplit) curSplit;
	this.context = curContext;

	if (null == rr) {
		rr = ReflectionUtils.newInstance(SequenceFileRecordReader.class, context.getConfiguration());
	}

	FileSplit fileSplit = new FileSplit(this.split.getPath(index),
			this.split.getOffset(index), this.split.getLength(index),
			this.split.getLocations());
	
	this.rr.initialize(fileSplit, this.context);
}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
private void openForRead(TaskAttemptContext taskAttemptContext)
        throws IOException, InterruptedException {
  reader = new SequenceFileRecordReader<K, V>();
  reader.initialize(new FileSplit(chunkFilePath, 0,
          DistCpUtils.getFileSize(chunkFilePath, configuration), null),
          taskAttemptContext);
}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
/**
 * Returns a reader for this split of the distributed cache file list.
 */
@Override
public RecordReader<LongWritable, BytesWritable> createRecordReader(
    InputSplit split, final TaskAttemptContext taskContext)
    throws IOException, InterruptedException {
  return new SequenceFileRecordReader<LongWritable, BytesWritable>();
}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
private void openForRead(TaskAttemptContext taskAttemptContext)
        throws IOException, InterruptedException {
  reader = new SequenceFileRecordReader<K, V>();
  reader.initialize(new FileSplit(chunkFilePath, 0,
          DistCpUtils.getFileSize(chunkFilePath,
              chunkContext.getConfiguration()), null), taskAttemptContext);
}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
@SuppressWarnings("unchecked")
public CombineSequenceFileRecordReader(CombineFileSplit split, TaskAttemptContext context, Integer index) throws IOException, InterruptedException {
	this.index = index;
	this.split = (CombineFileSplit) split;
	this.context = context;

	this.rr = ReflectionUtils.newInstance(SequenceFileRecordReader.class, context.getConfiguration());
}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
@Override
public RecordReader<NullWritable, V> createRecordReader(final InputSplit split, final TaskAttemptContext context)
        throws IOException, InterruptedException {
    final SequenceFileRecordReader<NullWritable, V> reader = new SequenceFileRecordReader<NullWritable, V>();
    reader.initialize(split, context);
    return reader;
}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
private void openForRead(TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
  reader = new SequenceFileRecordReader<>();
  reader.initialize(new FileSplit(chunkFilePath, 0, getFileSize(chunkFilePath, configuration), null),
      taskAttemptContext);
}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
/**
 * Getter for the record-reader, opened to the chunk-file.
 * @return Opened Sequence-file reader.
 */
public SequenceFileRecordReader<K,V> getReader() {
  assert reader != null : "Reader un-initialized!";
  return reader;
}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
@SuppressWarnings("unchecked")
@Override
public void prepareToRead(RecordReader reader, PigSplit split)
    throws IOException {
  this.reader = (SequenceFileRecordReader) reader;
}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
public VectorSequenceFileRecordReader() {
//		recordReader = new SequenceFileRecordReader<LongWritable, ArrayListWritable>();
		recordReader = new SequenceFileRecordReader<LongWritable, NumberListWritable<Double>>();
		pair = new PairOfByteBuffers();
	}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
@Override
public RecordReader<RecordKey, Text> getRecordReader(InputSplit split, TaskAttemptContext context, Integer index) {
  return new SequenceFileRecordReader<>();
}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
public SequenceFileAsJSONRecordBatchReader()
		throws IOException {
	sequenceFileRecordReader =
			new SequenceFileRecordReader<WritableComparable<?>, Writable>();
}
 

import org.apache.hadoop.mapreduce.lib.input.SequenceFileRecordReader; //导入依赖的package包/类
@SuppressWarnings("unchecked")
@Override
public void prepareToRead(RecordReader reader, PigSplit split)
      throws IOException {
  this.reader = (SequenceFileRecordReader) reader;
}