Avro Input Job

AvroRecordReader.java

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package org.apache.avro.mapred;

import java.io.IOException;

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.FileSplit;
import org.apache.hadoop.mapred.RecordReader;

import org.apache.avro.file.FileReader;
import org.apache.avro.file.DataFileReader;
import org.apache.avro.specific.SpecificDatumReader;
import org.apache.avro.reflect.ReflectDatumReader;

/** An {@link RecordReader} for Avro data files. */
public class AvroRecordReader<T>
  implements RecordReader<AvroWrapper<T>, NullWritable> {

  private FileReader<T> reader;
  private long start;
  private long end;

  public AvroRecordReader(JobConf job, FileSplit split)
    throws IOException {
    this(DataFileReader.openReader
         (new FsInput(split.getPath(), job),
          job.getBoolean(AvroJob.INPUT_IS_REFLECT, false)
          ? new ReflectDatumReader<T>(AvroJob.getInputSchema(job))
          : new SpecificDatumReader<T>(AvroJob.getInputSchema(job))),
         split);
  }

  

FlexibleAvroInputFormat.java

package de.xplosion.ds.xpredict.avro;

import java.io.IOException;

import org.apache.avro.generic.GenericRecord;
import org.apache.avro.mapred.AvroInputFormat;
import org.apache.avro.mapred.AvroWrapper;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapred.FileSplit;
import org.apache.hadoop.mapred.InputSplit;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.RecordReader;
import org.apache.hadoop.mapred.Reporter;

public class FlexibleAvroInputFormat extends AvroInputFormat<GenericRecord> {

    @Override
    public RecordReader<AvroWrapper<GenericRecord>, NullWritable> getRecordReader(InputSplit split,
            JobConf job, Reporter reporter) throws IOException {
        reporter.setStatus(split.toString());
        return new GenericAvroRecordReader(job, (FileSplit) split);
    }

}

GenericAvroRecordReader.java

package de.xplosion.ds.xpredict.avro;

import java.io.IOException;

import org.apache.avro.file.DataFileReader;
import org.apache.avro.generic.GenericDatumReader;
import org.apache.avro.generic.GenericRecord;
import org.apache.avro.mapred.AvroRecordReader;
import org.apache.avro.mapred.FsInput;
import org.apache.hadoop.mapred.FileSplit;
import org.apache.hadoop.mapred.JobConf;

public class GenericAvroRecordReader extends AvroRecordReader<GenericRecord> {

    public GenericAvroRecordReader(JobConf job, FileSplit split) throws IOException {
        super(DataFileReader.openReader(
                new FsInput(split.getPath(), job),
                new GenericDatumReader<GenericRecord>()),
                split);
    }
}