Hadoop-10-HDFS集群 Java实现MapReduce WordCount计算 Hadoop序列化 编写Mapper和Reducer和Driver 附带POM 详细代码 图文等内容

root@hecs-393573:/opt/wzk# ls
wordcount.txt
root@hecs-393573:/opt/wzk# hadoop fs -get /wzk/test/1.txt ./
root@hecs-393573:/opt/wzk# ls
1.txt  wordcount.txt
root@hecs-393573:/opt/wzk# hadoop fs -ls /
Found 5 items

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>org.example</groupId>
    <artifactId>hadoop-demo</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    </properties>

    <dependencies>
        <!-- Hadoop Dependencies -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.9.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.9.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-core</artifactId>
            <version>2.9.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-common</artifactId>
            <version>2.9.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>2.8.2</version>
        </dependency>
    </dependencies>

    <!--maven打包插件 -->
    <build>
        <plugins>
            <plugin>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>2.3.2</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>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

package icu.wzk.demo02;
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 {
        String line = value.toString();
        String[] words = line.split(" ");
        for (String word : words) {
            k.set(word);
            context.write(k, v);
        }
    }
}

package icu.wzk.demo02;

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> {

    int sum;
    IntWritable v = new IntWritable();

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

package icu.wzk.demo02;

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;

import java.io.IOException;

public class WordCountDriver {

    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
        // String inputPath = args[0];
        // String outputPath = args[1];

        // === 测试 ===
        String inputPath = "wc.txt";
        String outputPath = "wc-out";
        // =======

        // 配置
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);
        // 运行的类
        job.setJarByClass(WordCountDriver.class);
        // Mapper
        job.setMapperClass(WordCountMapper.class);
        // Reducer
        job.setReducerClass(WordCountReducer.class);
        // Map Output Key Value
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        // 最终 Key Value
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        // 路劲参数
        FileInputFormat.setInputPaths(job, new Path(inputPath));
        FileOutputFormat.setOutputPath(job, new Path(outputPath));
        // 等待结果
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }

}