在hadoop上执行字数统计作业

1.编写WordCount.java文件

package org.myorg;

import java.io.IOException;
import java.util.*;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;

public class WordCount {

public static class Map extends MapReduceBase implements Mapper {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();

public void map(LongWritable key, Text value, OutputCollector output, Reporter reporter) throws IOException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
output.collect(word, one);
}
}
}

public static class Reduce extends MapReduceBase implements Reducer {

public void reduce(Text key, Iterator values, OutputCollector output, Reporter reporter) throws IOException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
output.collect(key, new IntWritable(sum));
}
}

public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("wordcount");

conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);

conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);

conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);

FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));

JobClient.runJob(conf);
}

}

2.编译WordCount.java文件，把它制作成可执行jar包

    javac -d . -classpath $HADOOP_HOME/****-core.jar WordCount.java

3.在org的同级目录上建立manifest.mf

    在里面写上Main-Class: org.myorg.WordCount

4.保存并执行如下命令

    jar -cvfm count.jar manifest.mf org/

5.在hdfs上建立文件夹。

    hadoop fs -mkdir /test
    hadoop fs -mkdir /test/in

6.把wordtestnum.txt文件放入hdfs中

    hadoop fs -put /root/wordtestnum.txt /test

7.执行作业

    hadoop jar count.jar /test/in /test/out

8.查看运行结果

    hadoop fs -cat /test/out/part-00000