hadoop入门(四)

1.java开发map_reduce程序

2.配置系统环境变量HADOOP_HOME,指向hadoop安装目录(如果你不想招惹不必要的麻烦,不要在目录中包含空格或者中文字符)
把HADOOP_HOME/bin加到PATH环境变量(非必要,只是为了方便)
3.如果是在windows下开发,需要添加windows的库文件
(1).把盘中共享的bin目录覆盖HADOOP_HOME/bin
(2).如果还是不行,把其中的hadoop.dll复制到c:\windows\system32目录下,可能需要重启机器
4.建立新项目,引入hadoop需要的jar文件
5.代码WordMapper:

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
 
 
public class WordMapper extends Mapper {
 
    @Override
    protected void map(LongWritable key, Text value, Mapper.Context context)
            throws IOException, InterruptedException {
        String line = value.toString();
        String[] words = line.split(" ");
        for(String word : words) {
            context.write(new Text(word), new IntWritable(1));
        }
    }
     
}

6.代码WordReducer:

import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
 
public class WordReducer extends Reducer {
 
    @Override
    protected void reduce(Text key, Iterable values,
            Reducer.Context context) throws IOException, InterruptedException {
        long count = 0;
        for(IntWritable v : values) {
            count += v.get();
        }
        context.write(key, new LongWritable(count));
    }
     
}

7.代码Test:

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
 
 
public class Test {
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
                         
        Job job = Job.getInstance(conf);
         
        job.setMapperClass(WordMapper.class);
        job.setReducerClass(WordReducer.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);
         
        FileInputFormat.setInputPaths(job, "c:/bigdata/hadoop/test/test.txt");
        FileOutputFormat.setOutputPath(job, new Path("c:/bigdata/hadoop/test/out/"));
         
        job.waitForCompletion(true);
    }
}

8.在远程服务器执行

conf.set("fs.defaultFS", "hdfs://master:9000");
        
        conf.set("mapreduce.job.jar", "wc.jar");
        conf.set("mapreduce.framework.name", "yarn");
        conf.set("yarn.resourcemanager.hostname", "master");
        conf.set("mapreduce.app-submission.cross-platform", "true");

你可能感兴趣的:(hadoop入门(四))