1、运行Hadoop 自带的WordCount

准备数据

hadoop mapreduce  yarn
bigdata
hive sql
hello flink
spark flink  streaming

上传到HDFS 上

 hadoop  fs -put wc.txt  /test/wc

${HADOOP_HOME}/share/hadoop/mapreduce
WordCount 这个类就在hadoop-mapreduce-examples-2.9.2.jar 中

启动MR 任务

 hadoop  jar /root/bigdata/hadoop-2.9.2/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.9.2.jar  wordcount   /test/wc/wc.txt  /test/wc/wc_output

[root@master hadoop-2.9.2]# hadoop fs -text  /test/wc/wc_output/part-r-00000
bigdata 1
flink   2
hadoop  1
hello   1
hive    1
mapreduce       1
spark   1
sql     1
streaming       1
yarn    1
[root@master hadoop-2.9.2]#

2、 自定义实现Wordcount

map

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;
/**
 * 实现Map阶段的逻辑需要继承Mapper类并实现map方法
 * 前两个类型表时map输入kv对的类型
 * 后两个类型表时map输出kv对的类型
 * */
public class WordCountMapper extends  Mapper<LongWritable,Text, Text, IntWritable>{
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //super.map(key, value, context);
        //System.out.println("key="+key+" value="+value);
        String line = value.toString();
        String[] words = line.trim().replaceAll("\\s* ",",").split(",");
        for (String word : words) {
            context.write(new Text(word),new IntWritable(1));
        }
    }
}

reduce

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
import java.util.Iterator;
/**
 * 实现reduce阶段的逻辑需要继承Reduce类并实现reduce方法
 * 前两个类型表时reduce输入kv对的类型，要跟map的输出kv对的类型一致
 * 后两个类型表时reduce输出kv对的类型
 * */
public class WordCountReducer  extends Reducer<Text, IntWritable,Text,IntWritable> {
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum=  0;
        Iterator<IntWritable> iterator = values.iterator();
        while (iterator.hasNext()){
            IntWritable next = iterator.next();
            sum += next.get();
        }
        context.write(key,new IntWritable(sum));
    }
}

driver

import java.io.IOException;
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;
public class WordCountDriver {
 public static void main(String[] args) throws IOException,
         ClassNotFoundException, InterruptedException {
     //System.setProperty("hadoop.home.dir", "D:\\dev_soft\\hadoop-2.9.2");
     //System.load("D:\\dev_soft\\hadoop-2.9.2\\bin\\hadoop.dll");
     // 1 获取配置信息以及封装任务
     Configuration configuration = new Configuration();
     Job job = Job.getInstance(configuration);
     // 2 设置jar加载路径
     job.setJarByClass(WordCountDriver.class);
     // 3 设置map和reduce类
     job.setMapperClass(WordCountMapper.class);
     job.setReducerClass(WordCountReducer.class);
     // 4 设置map输出
     job.setMapOutputKeyClass(Text.class);
     job.setMapOutputValueClass(IntWritable.class);
     // 5 设置最终输出kv类型
     job.setOutputKeyClass(Text.class);
     job.setOutputValueClass(IntWritable.class);

     // 6 设置输⼊和输出路径
     // 本地模式  在program arguments设置参数
     FileInputFormat.setInputPaths(job, new Path(args[0]));
     FileOutputFormat.setOutputPath(job, new Path(args[1]));
     // 7 提交
     boolean result = job.waitForCompletion(true);
     System.exit(result ? 0 : 1);
 }
}

 maven 依赖可以看[添加链接描述](https://editor.csdn.net/md/?articleId=120251279 )    [这里面的]

打包，选择没有依赖的jar 上传

指定主类、输入和输出

hadoop  jar   wc-1.0-SNAPSHOT.jar   mr.WordCountDriver   /test/wc/wc.txt   /test/wc/wc_output2

[root@master test_data]# hadoop  fs -text /test/wc/wc_output2/part-r-00000
bigdata 1
flink   2
hadoop  1
hello   1
hive    1
mapreduce       1
spark   1
sql     1
streaming       1
yarn    1
[root@master test_data]# hadoop  fs -text /test/wc/wc_output/part-r-00000
bigdata 1
flink   2
hadoop  1
hello   1
hive    1
mapreduce       1
spark   1
sql     1
streaming       1
yarn    1
[root@master test_data]#