org.apache.hadoop.mapred.MultiFileInputFormat Maven / Gradle / Ivy

/**
 * 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.hadoop.mapred;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.FileUtil;
import org.apache.hadoop.fs.Path;

/**
 * An abstract {@link InputFormat} that returns {@link MultiFileSplit}'s
 * in {@link #getSplits(JobConf, int)} method. Splits are constructed from 
 * the files under the input paths. Each split returned contains nearly
 * equal content length. 
  
 * Subclasses implement {@link #getRecordReader(InputSplit, JobConf, Reporter)}
 * to construct RecordReader's for MultiFileSplit's.
 * @see MultiFileSplit
 */
@InterfaceAudience.Public
@InterfaceStability.Stable
public abstract class MultiFileInputFormat
  extends FileInputFormat {

  @Override
  public InputSplit[] getSplits(JobConf job, int numSplits) 
    throws IOException {
    
    Path[] paths = FileUtil.stat2Paths(listStatus(job));
    List splits = new ArrayList(Math.min(numSplits, paths.length));
    if (paths.length != 0) {
      // HADOOP-1818: Manage splits only if there are paths
      long[] lengths = new long[paths.length];
      long totLength = 0;
      for(int i=0; i= goalLength) {
        return i - startIndex + 1;
      }
    }
    return lengths.length - startIndex;
  }
  
  @Override
  public abstract RecordReader getRecordReader(InputSplit split,
      JobConf job, Reporter reporter)
      throws IOException;
}