MapReduce实现wordcount案例

MapReduce实现wordcount案例

1、创建maven工程

导入hadoop所需要的依赖包

	<!--  你的hadoop版本信息  -->
    <properties>
        <hadoop.version>3.1.4</hadoop.version>
    </properties>

    <!--  hadoop运行所需要的依赖包  -->
    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/junit/junit -->
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.testng</groupId>
            <artifactId>testng</artifactId>
            <version>RELEASE</version>
        </dependency>
        <!--    显示日志所需要的依赖包    -->
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.17</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.0</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                    <!--   <verbal>true</verbal>-->
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.4.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <minimizeJar>true</minimizeJar>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>

2、创建自定义的Mapper逻辑

package 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 WordMapper extends Mapper<LongWritable, Text,Text, IntWritable> {

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //这个value指的是一行文本数据
        String s = value.toString();
        //把一行文本数据，按照“，”的方式进行切割
        String[] split = s.split(",");
        for (String word:split) {
            //每个数据，一个单词，对应的value值是1
            context.write(new Text(word),new IntWritable(1));
        }
    }
}

3、自定义Mapper类

package 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 WordReduce extends Reducer<Text, IntWritable,Text,IntWritable> {

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 0;
        for (IntWritable value:values) {
            sum = sum + value.get();
        }
        context.write(key,new IntWritable(sum));
    }
}

4、自定义测试类

package 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.Job;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.log4j.BasicConfigurator;

import java.io.IOException;

public class Test {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //这一句话是为了能打印日志的，进行的配置
        BasicConfigurator.configure();

        //1、获取到我们的job对象，让它运行
        Job job = Job.getInstance(new Configuration(), "WordCount");

        //2、如果我们打包成jar文件，指定我们程序的入口类是哪一个
        job.setJarByClass(Test.class);

        //3、从存储系统中获取到什么样的文件，这里指的是Text这样的输入流文件
        job.setInputFormatClass(TextInputFormat.class);
        //4、指定输入流文件的位置
        TextInputFormat.addInputPath(job,new Path("E:\\hadoop\\mapreduce\\input"));

        //5、设置自定义的Mapper
        job.setMapperClass(WordMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        //6、设置自定义的Reduce
        job.setReducerClass(WordReduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        //7、设置Reduce个数
        job.setNumReduceTasks(1);

        //8、设置输出的文件以什么类型存储，这里是Text形式的输出流
        job.setOutputFormatClass(TextOutputFormat.class);
        //9、输出的文件夹的位置（文件中不能存在这个文件夹）
        TextOutputFormat.setOutputPath(job,new Path("E:\\hadoop\\mapreduce\\output\\text19"));

        //10、等待结果输出
        boolean b = job.waitForCompletion(true);

        //11、退出
        System.exit(b?0:1);


    }
}