/**
* 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.examples;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.MultipleInputs;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
/**
* NewMultiFileWordCount is an example to demonstrate the usage of
* MultipleInputs. This examples counts the occurrences of words in the
* text files under the given input directory.
*/
public class NewMultiFileWordCount extends Configured implements Tool {
/**
* This Mapper is similar to the one in {@link HadoopTest.MapClass}.
*/
public static class MapClass extends Mapper<LongWritable, Text, Text, LongWritable> {
private final static LongWritable one = new LongWritable(1);
private Text word = new Text();
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer itr = new StringTokenizer(line);
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
private void printUsage() {
System.out.println("Usage : multifilewc <input_dir> <output>");
}
public int run(String[] args) throws Exception {
if (args.length < 2) {
printUsage();
return 1;
}
Job job = new Job(getConf());
job.setJobName("MultiFileWordCount");
job.setJarByClass(NewMultiFileWordCount.class);
// the keys are words (strings)
job.setOutputKeyClass(Text.class);
// the values are counts (ints)
job.setOutputValueClass(LongWritable.class);
// use the WordCount Reducer
job.setCombinerClass(LongSumReducer.class);
job.setReducerClass(LongSumReducer.class);
MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, MapClass.class);
MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, MapClass.class);
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
return 0;
}
public static void main(String[] args) throws Exception {
int ret = ToolRunner.run(new NewMultiFileWordCount(), args);
System.exit(ret);
}
* 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.examples;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.MultipleInputs;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
/**
* NewMultiFileWordCount is an example to demonstrate the usage of
* MultipleInputs. This examples counts the occurrences of words in the
* text files under the given input directory.
*/
public class NewMultiFileWordCount extends Configured implements Tool {
/**
* This Mapper is similar to the one in {@link HadoopTest.MapClass}.
*/
public static class MapClass extends Mapper<LongWritable, Text, Text, LongWritable> {
private final static LongWritable one = new LongWritable(1);
private Text word = new Text();
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer itr = new StringTokenizer(line);
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
private void printUsage() {
System.out.println("Usage : multifilewc <input_dir> <output>");
}
public int run(String[] args) throws Exception {
if (args.length < 2) {
printUsage();
return 1;
}
Job job = new Job(getConf());
job.setJobName("MultiFileWordCount");
job.setJarByClass(NewMultiFileWordCount.class);
// the keys are words (strings)
job.setOutputKeyClass(Text.class);
// the values are counts (ints)
job.setOutputValueClass(LongWritable.class);
// use the WordCount Reducer
job.setCombinerClass(LongSumReducer.class);
job.setReducerClass(LongSumReducer.class);
MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, MapClass.class);
MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, MapClass.class);
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
return 0;
}
public static void main(String[] args) throws Exception {
int ret = ToolRunner.run(new NewMultiFileWordCount(), args);
System.exit(ret);
}
}
如果错误还望指点一二!!!