hadoop 运行java程序_hadoop上运行java程序（zz）

hadoop上运行java程序(zz)

(2011-04-19 15:31:49)

标签：

杂谈

建立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

IntWritable> {

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

IntWritable> {

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);

}

}

然后编译WordCount.java文件，把它制作成可执行jar包

javac -d . -classpath /root/hadoop-0.20.1/hadoop-0.20.1-core.jar

WordCount.java

然后在org的同级目录上建立manifest.mf

在里面写上Main-Class: org.myorg.WordCount

然后保存并执行jar -cvfm count.jar manifest.mf org/

然后在hdfs上建立一个文件夹，hadoop fs -mkdir /test

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

然后执行hadoop jar /root/Desktop/count.jar /test/in /test/out

查看运行结果hadoop fs -cat /test/out/part-00000

分享：

喜欢

0

赠金笔

加载中，请稍候......

评论加载中，请稍候...

发评论

登录名： 密码： 找回密码 注册记住登录状态

昵   称：

评论并转载此博文

发评论

以上网友发言只代表其个人观点，不代表新浪网的观点或立场。