MapreduceAPI（wordcount）

pom.xml依赖

<?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>com.atguigu</groupId>
    <artifactId>mapreduce200105</artifactId>
    <version>1.0-SNAPSHOT</version>
    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>7</source>
                    <target>7</target>
                </configuration>
            </plugin>
        </plugins>
    </build>

    <dependencies>
        <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>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>3.1.3</version>
        </dependency>
        <!--<dependency>-->
        <!--<groupId>org.apache.hadoop</groupId>-->
        <!--<artifactId>hadoop-client-runtime</artifactId>-->
        <!--<version>3.1.3</version>-->
        <!--</dependency>-->
    </dependencies>
</project>

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>

log4j.properties

log4j.rootLogger=INFO, stdout
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%d %p [%c] - %m%n
log4j.appender.logfile=org.apache.log4j.FileAppender
log4j.appender.logfile.File=target/spring.log
log4j.appender.logfile.layout=org.apache.log4j.PatternLayout
log4j.appender.logfile.layout.ConversionPattern=%d %p [%c] - %m%n

Mapper

package com.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 WcMapper extends Mapper<LongWritable,Text, Text, IntWritable> {
    private Text word = new Text();
    private IntWritable one = new IntWritable(1);

    /**
     * 框架将数据拆除一行一行输入进来，我们把数据编程（单词，1）的形式
     * @param key 行号
     * @param value 行内容
     * @param context 任务本事
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //拿到一行数据
        String line = value.toString();
        //将这一行拆分成多个单词
        String[] words = line.split(" ");
        //将（单词，1）写回框架
        for (String word : words) {
            this.word.set(word);
        context.write(this.word,this.one);
        }
        }
        }

Reducer

package com.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 WcReducer extends Reducer<Text, IntWritable,Text, IntWritable> {
    private IntWritable result = new IntWritable();
    /**
     * 框架把数据按照单词分好组输入给reducer，reducer将统一单词计数累加
     * @param key 单词
     * @param values 单词出现的次数
     * @param context 任务本身
     * @throws IOException
     * @throws InterruptedException
     */
    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        //做累加
        int sum = 0;
        for (IntWritable value : values) {
            sum += value.get();
        }
        //包装结果并输出
        result.set(sum);
        context.write(key,result);

    }
}

Driver 

package com.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.io.compress.BZip2Codec;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.io.compress.SnappyCodec;
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 WcDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        //1.先获取Job实例
        Configuration configuration = new Configuration();

        configuration.set("fs.defaultFS", "hdfs://hadoop101:8020");
        configuration.set("mapreduce.framework.name","yarn");
        configuration.set("mapreduce.app-submission.cross-platform","true");
        configuration.set("yarn.resourcemanager.hostname","hadoop102");

        configuration.set("mapred.job.queue.name","hive");

//        // 开启map端输出压缩
//        configuration.setBoolean("mapreduce.map.output.compress", true);
//        // 设置map端输出压缩方式
//       configuration.setClass("mapreduce.map.output.compress.codec", SnappyCodec.class,CompressionCodec.class);

        Job job = Job.getInstance(configuration);
        //2.设置Jar包
       // job.setJarByClass(WcDriver.class);
        job.setJar("D:\\mywork\\IDEAproject\\mapreduce\\target\\mapreduce200105-1.0-SNAPSHOT.jar");


        //3.设置Mapper和Reducer
        job.setMapperClass(WcMapper.class);
        job.setReducerClass(WcReducer.class);
        //4.设置Map和Reduce的输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        //5.设置输入输出文件
        //5-1)设置输入路径
        FileInputFormat.setInputPaths(job,new Path(args[0]));
        FileOutputFormat.setOutputPath(job,new Path(args[1]));
//
//        // 设置reduce端输出压缩开启
//        FileOutputFormat.setCompressOutput(job, true);
//
//        // 设置压缩的方式
//        FileOutputFormat.setOutputCompressorClass(job, BZip2Codec.class);

        //6.提交Job
        boolean b = job.waitForCompletion(true);

        System.exit(b ? 0 : 1);
    }
}