hadoop2.7.2 wordcount案例

<!--依赖--> 
   <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>

        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.7.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>2.19.0</version>
        </dependency>

<!--打包-->
    <build>
        <plugins>
            <plugin>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.8.1</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
            <plugin>
                <artifactId>maven-assembly-plugin </artifactId>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                    <archive>
                        <manifest>
                            <mainClass>com.hxy.mr.wordcount.WordCountDriver</mainClass>
                        </manifest>
                    </archive>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

package com.hxy.mr.wordcount;

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 WordcountMapper extends Mapper<LongWritable, Text,Text, IntWritable>{

    Text k = new Text();
    IntWritable v = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
        //获取第一行数据
        String line = value.toString();

        //切割单词
        String[] words = line.split(" ");

        //循环写出
        for (String word : words) {
            k.set(word);
            context.write(k,v); //写入缓冲区
        }
    }
}

package com.hxy.mr.wordcount;

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

import java.io.IOException;

public class WordCountReducer extends Reducer<Text, IntWritable,Text,IntWritable> {

    IntWritable v = new IntWritable();
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {

        //值求和
        int sum=0;
        for (IntWritable value : values) {
            sum += value.get();
        }
        v.set(sum);
        context.write(key,v);
    }
}

package com.hxy.mr.wordcount;

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.Cluster;
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 WordCountDriver {
    private static Configuration conf =new Configuration();

    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        
        //获取job对象
        Job job = Job.getInstance(conf);

        //设置jar位置
        job.setJarByClass(WordCountDriver.class);

        //关联mapper与reducer
        job.setMapperClass(WordcountMapper.class);
        job.setReducerClass(WordCountReducer.class);

        //设置mapper的输出k、v类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //设置最终数据输出的k、v类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置程序运行的输入数据与输出数据地址
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));

        //提交任务
        job.waitForCompletion(true);

    }
}

#????DEBUG????????console?file???????console?file?????????
log4j.rootLogger=DEBUG,console

#??????????
log4j.appender.console = org.apache.log4j.ConsoleAppender
log4j.appender.console.Target = System.out
log4j.appender.console.Threshold=DEBUG
log4j.appender.console.layout = org.apache.log4j.PatternLayout
log4j.appender.console.layout.ConversionPattern=[%c]-%m%n