一、 hadoop环境配置

需要用到的工具

jdk（我的是1.8）

hadoop-eclipse-plugin-2.6.5.jar（这里我提供已编译好的包下载地址，若是其他版本可自行搜索或用ant和hadoop源代码自行编译）

eclipse（我的版本是eclipse-standard-luna-R-linux-gtk-x86_64.tar.gz）

hadoop-2.7.0.tar.gz

二、 eclipse

1. 下载解压eclipse，解压

sudo tar -zxvf eclipse-standard-luna-R-linux-gtk-x86_64.tar.gz

点击eclipse中的eclipse.ini文件打开eclipse

2. eclipse打开报错

解决，进入eclipse的jre目录，将javabin目录链接到eclipse中

cd ./eclipse/jre
sudo ln -s /usr/local/java-8-openjdk-amd64/bin/ bin

3. 打开eclipse > window > perference搜索mapreduce，添加hadoop目录

4. 显示hadoop连接配置界面Windows > show view > other

5. 在Map.Reduce Locations中右键 > new application

6. 打开mapreduce的hdfs，在左侧就有hdfs目录了

8. 新建mapreduce project

9. 新建包和类输入测试代码

package com.hadoop.test;
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> [<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);  
    for (int i = 0; i < otherArgs.length - 1; ++i) {  
      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));  
    }  
    FileOutputFormat.setOutputPath(job,  
      new Path(otherArgs[otherArgs.length - 1]));  
    System.exit(job.waitForCompletion(true) ? 0 : 1);  
  }  

 															}

10. 创建单词文件，并上传到hdfs上

11. 右键》run As 》run on configuration，输出

hadoop2.7+eclipse的配置

一、 hadoop环境配置

二、 eclipse

猜你喜欢