MapReduce基础

Posted 2021-02-08 zhouhb

1. WordCount程序

1.1 WordCount源程序

import java.io.IOException;
import java.util.Iterator;
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 WordCount() {
    }
     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 = Job.getInstance(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(WordCount.TokenizerMapper.class);
        job.setCombinerClass(WordCount.IntSumReducer.class);
        job.setReducerClass(WordCount.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);
    }
    public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
        private static final IntWritable one = new IntWritable(1);
        private Text word = new Text();
        public TokenizerMapper() {
        }
        public void map(Object key, Text value, Mapper<Object, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString()); 
            while(itr.hasMoreTokens()) {
                this.word.set(itr.nextToken());
                context.write(this.word, one);
            }
        }
    }
public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
        private IntWritable result = new IntWritable();
        public IntSumReducer() {
        }
        public void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
            int sum = 0;
            IntWritable val;
            for(Iterator i$ = values.iterator(); i$.hasNext(); sum += val.get()) {
                val = (IntWritable)i$.next();
            }
            this.result.set(sum);
            context.write(key, this.result);
        }
    }
}

 

1.2 运行程序，Run As->Java Applicatiion

1.3 编译打包程序，产生Jar文件

 

2 运行程序

2.1 建立要统计词频的文本文件

wordfile1.txt

Spark Hadoop

Big Data

wordfile2.txt

Spark Hadoop

Big Cloud

2.2 启动hdfs，新建input文件夹，上传词频文件

cd /usr/local/hadoop/

./sbin/start-dfs.sh 

./bin/hadoop fs -mkdir input

./bin/hadoop fs -put /home/hadoop/wordfile1.txt input

./bin/hadoop fs -put /home/hadoop/wordfile2.txt input

2.3 查看已上传的词频文件：

[email protected]:/usr/local/hadoop$ ./bin/hadoop fs -ls .
Found 2 items
drwxr-xr-x - hadoop supergroup 0 2019-02-11 15:40 input
-rw-r--r-- 1 hadoop supergroup 5 2019-02-10 20:22 test.txt
[email protected]:/usr/local/hadoop$ ./bin/hadoop fs -ls ./input
Found 2 items
-rw-r--r-- 1 hadoop supergroup 27 2019-02-11 15:40 input/wordfile1.txt
-rw-r--r-- 1 hadoop supergroup 29 2019-02-11 15:40 input/wordfile2.txt

2.4 运行WordCount

./bin/hadoop jar /home/hadoop/WordCount.jar input output

屏幕上会输入大段信息

 然后可以查看运行结果：

[email protected]:/usr/local/hadoop$ ./bin/hadoop fs -cat output/*
Hadoop 2
Spark 2
---