大数据离线计算Hadoop2.x 学习笔记（3）- HDFS写入分析 和 MR

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u012292754/article/details/85599316

1 HDFS 写入分析

public class TestHDFS {
    public void testWrite() throws IOException {
        Configuration conf = new Configuration();
        FileSystem fs = FileSystem.get(conf);
        Path path = new Path("/test/a.txt");

        FSDataOutputStream fout = fs.create(path);
        fout.write("Hello World".getBytes());
        fout.close();
    }
 }

2 MR

file:///d:/wc
d前面的 /  代表根目录

2.1 单词统计

• WCMapper.java

package mr;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class WCMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

    Text keyOut = new Text();
    IntWritable valueOut = new IntWritable();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] arr = value.toString().split(" ");
        for (String s : arr) {
            keyOut.set(s);
            valueOut.set(1);
            context.write(keyOut,valueOut);
        }
    }
}

• WCReducer.java

package mr;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class WCReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int count = 0;
        for (IntWritable iw : values) {
            count = count + iw.get();
        }
        context.write(key,new IntWritable(count));
    }
}

• WCApp.java

package mr;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.io.IOException;

public class WCApp {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        Configuration conf = new Configuration();

        Job job = Job.getInstance(conf);

        FileInputFormat.addInputPath(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        job.setJobName("WCApp");
        job.setJarByClass(WCApp.class);

        job.setMapperClass(WCMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setReducerClass(WCReducer.class);
        job.setNumReduceTasks(1);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        job.waitForCompletion(false);


    }
}