Many resources are needed to download a project. Please understand that we have to compensate our server costs. Thank you in advance. Project price only 1 $
You can buy this project and download/modify it how often you want.
/**
* 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 org.apache.hadoop.shaded.com.liance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org.apache.hadoop.shaded.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.shaded.org.apache.hadoop.mapred.lib;
import java.org.apache.hadoop.shaded.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.LinkedList;
import java.util.List;
import java.util.Map;
import java.util.Map.Entry;
import org.apache.hadoop.shaded.org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.shaded.org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.shaded.org.apache.hadoop.fs.Path;
import org.apache.hadoop.shaded.org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.shaded.org.apache.hadoop.mapred.InputFormat;
import org.apache.hadoop.shaded.org.apache.hadoop.mapred.InputSplit;
import org.apache.hadoop.shaded.org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.shaded.org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.shaded.org.apache.hadoop.mapred.RecordReader;
import org.apache.hadoop.shaded.org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.shaded.org.apache.hadoop.util.ReflectionUtils;
/**
* An {@link InputFormat} that delegates behaviour of paths to multiple other
* InputFormats.
*
* @see MultipleInputs#addInputPath(JobConf, Path, Class, Class)
*/
@InterfaceAudience.Private
@InterfaceStability.Unstable
public class DelegatingInputFormat implements InputFormat {
public InputSplit[] getSplits(JobConf conf, int numSplits) throws IOException {
JobConf confCopy = new JobConf(conf);
List splits = new ArrayList();
Map formatMap = MultipleInputs.getInputFormatMap(conf);
Map> mapperMap = MultipleInputs
.getMapperTypeMap(conf);
Map, List> formatPaths
= new HashMap, List>();
// First, build a map of InputFormats to Paths
for (Entry entry : formatMap.entrySet()) {
if (!formatPaths.containsKey(entry.getValue().getClass())) {
formatPaths.put(entry.getValue().getClass(), new LinkedList());
}
formatPaths.get(entry.getValue().getClass()).add(entry.getKey());
}
for (Entry, List> formatEntry :
formatPaths.entrySet()) {
Class formatClass = formatEntry.getKey();
InputFormat format = (InputFormat) ReflectionUtils.newInstance(
formatClass, conf);
List paths = formatEntry.getValue();
Map, List> mapperPaths
= new HashMap, List>();
// Now, for each set of paths that have a org.apache.hadoop.shaded.com.on InputFormat, build
// a map of Mappers to the paths they're used for
for (Path path : paths) {
Class mapperClass = mapperMap.get(path);
if (!mapperPaths.containsKey(mapperClass)) {
mapperPaths.put(mapperClass, new LinkedList());
}
mapperPaths.get(mapperClass).add(path);
}
// Now each set of paths that has a org.apache.hadoop.shaded.com.on InputFormat and Mapper can
// be added to the same job, and split together.
for (Entry, List> mapEntry : mapperPaths
.entrySet()) {
paths = mapEntry.getValue();
Class mapperClass = mapEntry.getKey();
if (mapperClass == null) {
mapperClass = conf.getMapperClass();
}
FileInputFormat.setInputPaths(confCopy, paths.toArray(new Path[paths
.size()]));
// Get splits for each input path and tag with InputFormat
// and Mapper types by wrapping in a TaggedInputSplit.
InputSplit[] pathSplits = format.getSplits(confCopy, numSplits);
for (InputSplit pathSplit : pathSplits) {
splits.add(new TaggedInputSplit(pathSplit, conf, format.getClass(),
mapperClass));
}
}
}
return splits.toArray(new InputSplit[splits.size()]);
}
@SuppressWarnings("unchecked")
public RecordReader getRecordReader(InputSplit split, JobConf conf,
Reporter reporter) throws IOException {
// Find the InputFormat and then the RecordReader from the
// TaggedInputSplit.
TaggedInputSplit taggedInputSplit = (TaggedInputSplit) split;
InputFormat inputFormat = (InputFormat) ReflectionUtils
.newInstance(taggedInputSplit.getInputFormatClass(), conf);
return inputFormat.getRecordReader(taggedInputSplit.getInputSplit(), conf,
reporter);
}
}
