1). 用Maven创建一个标准化的Java项目
mvn archetype:generate -DarchetypeGroupId=org.apache.maven.archetypes -DgroupId=com.jason.hadoop.example -DartifactId=hadoopExample -DpackageName=com.jason.hadoop.example-Dversion=1.0-SNAPSHOT -DinteractiveMode=false
2).进入项目,执行mvn命令
cd hadoopExample/
mvn clean install
3).生成eclipse工程文件
mvn eclipse:eclipse
4)导入项目到eclipse
5).增加hadoop依赖
这里我使用hadoop-1.0.1版本,在eclipse里修改文件:pom.xml
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-core</artifactId>
<version>1.0.1</version>
</dependency>
<dependency>
6)下载依赖
mvn clean install
7)从新生成eclipse工程文件
mvn eclipse:eclipse
8)从Hadoop集群环境下载hadoop配置文件
core-site.xml
hdfs-site.xml
mapred-site.xml
保存在src/main/resources/hadoop目录下面
9)编写一个简单的MapReduce程序,实现wordcount功能。
新建一个Java文件:WordCount.java
package com.jason.hadoop.example;
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);
}
conf.addResource("classpath:/hadoop/core-site.xml");
conf.addResource("classpath:/hadoop/hdfs-site.xml");
conf.addResource("classpath:/hadoop/mapred-site.xml");
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);
}
}
运行该程序,arguments填写以下参数(其中input目录要先建好,output目录如果存在要删掉)
hdfs://localhost:9000/input hdfs://localhost:9000/output