myeclipse下搭建hadoop2.7.3開發環境

本文轉載自查看原文 2016-11-12 17:14 8975

需要下載的文件：鏈接：http://pan.baidu.com/s/1i5yRyuh 密碼：ms91

一下載並編譯 hadoop-eclipse-plugin-2.7.3.jar

二將hadoop-eclipse-plugin-2.7.3.jar放到myeclipse的安裝目錄下的plugins目錄下，並重啟myeclipse

　　在windows->preferences下可看見hadoop Map/Reduce界面，路徑選擇你WINDOWS下的hadoop解壓后的路徑。

三選擇Windows->show view->others下的MapReduce Locations

四新建一個配置配置如下

host為你的遠程hadoop待連接的主機IP地址

Port:50030 對應mapred-site.xml下的jobtracher地址，如下

Port:9000對應core-site.xml下的fs.default.name的端口

user name 填你windows的用戶名；

修改Advanced parameters下的參數

值對應 core-site.xml下的hadoop.tmp.dir參數

修改hdfs-site.xml下的dfs.permissions參數，允許連接

四保存配置參數並重啟myeclipse,可以看見如下的文件結構說明配置連接成功。

五下載hadoop.ll和winutils.exe 到windows的hadoop/bin目錄下

並將hadoop.dll添加到windows->system32目錄下

五環境測試

　　新建項目：File-->New-->Other-->Map/Reduce Project ,項目名可以隨便取

　　它會自動添加依賴包，如下：

新建如下文件：

編寫實現代碼，與官方例子為例

package com.duking.hadoop;

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(otherArgs.length);
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);
}
}