jjeong

http://hadoop.apache.org/common/docs/current/mapred_tutorial.html
http://hadoop.apache.org/common/docs/r0.20.0/hdfs_shell.html

- 일단 hadoop-0.21.0 으로 위에 tutorial 을 보고 시작 하였습니다.
- 바로 문제 봉착....
- 일단 classpath 문제로 생각해서 설정을 막 해보았으나 잘 안됩니다.
- 그래서 hadoop*.jar 를 모두 풀어서 걍 hadoop-0.21.0-core.jar 로 묶어 버렸습니다.
- 이렇게 해서 classpath 에 hadoop-0.21.0-core.jar 를 설정해 주고 compile 하니 Success!!
- hadoop-0.20.0 부터 하위 버전에는 그냥 hadoop*core.jar 가 tar.gz 파일에 들어 있습니다.

/**
 * 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.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {

  public static class TokenizerMapper
       extends Mapper<Object, Text, Text, IntWritable>{
   
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
     
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);
      }
    }
  }
 
  public static class IntSumReducer
       extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();

    public void reduce(Text key, Iterable<IntWritable> values,
                       Context context
                       ) throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
      result.set(sum);
      context.write(key, result);
    }
  }

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
      System.err.println("Usage: wordcount <in> <out>");
      System.exit(2);
    }
    Job job = new Job(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

cd $HADOOP_HOME
mkdir example
ubuntu:~/app/hadoop$ javac -cp ./hadoop-0.21.0-core.jar:./lib/commons-cli-1.2.jar -d example WordCount.java
ubuntu:~/app/hadoop$ jar cvf wordcount.jar -C example/ .

- 먼저 테스트할 파일을 생성 합니다.
cd $HADOOP_HOME/example
vi file01

vi file02

ubuntu:~/app/hadoop/example$ ../bin/hadoop fs -mkdir input
ubuntu:~/app/hadoop/example$ ../bin/hadoop fs -put file01 ./input/
ubuntu:~/app/hadoop/example$ ../bin/hadoop fs -put file02 ./input/
ubuntu:~/app/hadoop/example$ ../bin/hadoop jar ../wordcount.jar org.apache.hadoop.examples.WordCount input output
ubuntu:~/app/hadoop/example$ ../bin/hadoop jar ../wordcount.jar org.apache.hadoop.examples.WordCount input output

cd $HADOOP_HOME
mkdir hadoop-0.21.0-core
cp *.jar ./hadoop-0.21.0-core/
cd ./hadoop-0.21.0
jar xvf hadoop-hdfs-ant-0.21.0.jar          
jar xvf hadoop-mapred-examples-0.21.0.jar
jar xvf hadoop-common-0.21.0.jar       
jar xvf hadoop-hdfs-test-0.21.0-sources.jar 
jar xvf hadoop-mapred-test-0.21.0.jar
jar xvf hadoop-common-test-0.21.0.jar  
jar xvf hadoop-hdfs-test-0.21.0.jar         
jar xvf hadoop-mapred-tools-0.21.0.jar
jar xvf hadoop-hdfs-0.21.0-sources.jar 
jar xvf hadoop-mapred-0.21.0-sources.jar
jar xvf hadoop-hdfs-0.21.0.jar         
jar xvf hadoop-mapred-0.21.0.jar
# org 폴더만 남기고 모든 파일 및 폴더를 삭제 합니다.
cd ..
jar cvf hadoop-0.21.0-core.jar -C hadoop-0.21.0-core/ .
# 이제 ls -al 해 보시면 hadoop-0.21.0-core.jar 가 생성된걸 보실 수 있습니다.
# 완전 노가다 방법이니.. 걍 참고만 하시길..