WordCount案例

1.创建maven工程Mapreduce-demo，导入相关依赖，以下是pom.xml

<?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>Mapreduce-demo</artifactId>
    <version>1.0-SNAPSHOT</version>
    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-slf4j-impl</artifactId>
            <version>2.12.0</version>
        </dependency>
    </dependencies>

</project>

2.在src/main/resources目录下，新建一个文件，命名为“log4j2.xml”，以下为log4j2.xml

<?xml version="1.0" encoding="UTF-8"?>
<Configuration status="error" strict="true" name="XMLConfig">
    <Appenders>
        <!-- 类型名为Console，名称为必须属性 -->
        <Appender type="Console" name="STDOUT">
            <!-- 布局为PatternLayout的方式，
            输出样式为[INFO] [2018-01-22 17:34:01][org.test.Console]I'm here -->
            <Layout type="PatternLayout"
                    pattern="[%p] [%d{yyyy-MM-dd HH:mm:ss}][%c{10}]%m%n" />
        </Appender>

    </Appenders>

    <Loggers>
        <!-- 可加性为false -->
        <Logger name="test" level="info" additivity="false">
            <AppenderRef ref="STDOUT" />
        </Logger>

        <!-- root loggerConfig设置 -->
        <Root level="info">
            <AppenderRef ref="STDOUT" />
        </Root>
    </Loggers>

</Configuration>

3.编写WordCountMapper、WordCountReducer、WordCountDriver类

package com.xbd.mapreduce.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> {
    private Text outkey;
    private IntWritable outvalue;
    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        outkey=new Text();
        outvalue=new IntWritable(1);
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        String[] words = line.split(" ");
        for (String word : words) {
            outkey.set(word);
            context.write(outkey,outvalue);
        }
    }
}

package com.xbd.mapreduce.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> {
    private IntWritable outvalue;
    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        outvalue=new IntWritable();
    }

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

package com.xbd.mapreduce.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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

public class WordCountDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        // 1 获取配置信息并创建job对象
        Job job = Job.getInstance(new Configuration());
        // 2 关联本Driver程序的jar
        job.setJarByClass(WordCountDriver.class);
        // 3 关联Mapper和Reducer的jar
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        // 4 设置Mapper输出的kv类型
        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
        FileInputFormat.setInputPaths(job,new Path("E:\\学习\\wordcount\\input\\word.txt"));
        FileOutputFormat.setOutputPath(job,new Path("E:\\学习\\wordcount\\output"));
        // 7 提交job
        job.waitForCompletion(true);
    }
}