1). 用Maven建立一個標準化的Java項目
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).進入項目,執行mvn命令
cd hadoopExample/
mvn clean install
3).生成eclipse工程文件
mvn eclipse:eclipse
4)導入項目到eclipse
5).增長hadoop依賴
這裏我使用hadoop-1.0.1版本,在eclipse裏修改文件:pom.xml
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-core</artifactId>
<version>1.0.1</version>
</dependency>
<dependency>
6)下載依賴
mvn clean install
7)重新生成eclipse工程文件
mvn eclipse:eclipse
8)從Hadoop集羣環境下載hadoop配置文件
core-site.xml
hdfs-site.xml
mapred-site.xml
保存在src/main/resources/hadoop目錄下面
9)編寫一個簡單的MapReduce程序,實現wordcount功能。
新建一個Java文件:WordCount.java
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); } }
運行該程序,arguments填寫如下參數(其中input目錄要先建好,output目錄若是存在要刪掉)
hdfs://localhost:9000/input hdfs://localhost:9000/output
apache