MapReduce快速入门系列(2) | 统计输出给定的文本文档每一个单词出现的总次数

    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>RELEASE</version>
        </dependency>
        <dependency>
            <groupId>org.apache.logging.log4j</groupId>
            <artifactId>log4j-core</artifactId>
            <version>2.8.2</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>jdk.tools</groupId>
            <artifactId>jdk.tools</artifactId>
            <version>1.8</version>
            <scope>system</scope>
            <systemPath>D:/java/jdk-1.8.0/lib/tools.jar</systemPath>
        </dependency>
    </dependencies>

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

package com.buwenbuhuo.wordcount;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

/**
 * @author 卜温不火
 * @create 2020-04-22 21:24
 * com.buwenbuhuo.wordcount - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class WcMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

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

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

        // 1 获取一行
        String line = value.toString();

        // 2 切割
        String[] words = line.split(" ");

        // 3 输出
        for (String word : words) {

            k.set(word);
            context.write(k, v);
        }
    }
}

package com.buwenbuhuo.wordcount;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;


/**
 * @author 卜温不火
 * @create 2020-04-22 21:24
 * com.buwenbuhuo.wordcount - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class WcReducer extends Reducer<Text, IntWritable, Text, IntWritable>{

    int sum;
    IntWritable v = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {

        // 1 累加求和
        sum = 0;
        for (IntWritable count : values) {
            sum += count.get();
        }

        // 2 输出
        v.set(sum);
        context.write(key,v);
    }
}

package com.buwenbuhuo.wordcount;
import java.io.IOException;
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;

/**
 * @author 卜温不火
 * @create 2020-04-22 21:24
 * com.buwenbuhuo.wordcount - the name of the target package where the new class or interface will be created.
 * mapreduce0422 - the name of the current project.
 */
public class WcDriver {

    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

        // 1 获取配置信息以及封装任务
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        // 2 设置jar加载路径
        job.setJarByClass(WcDriver.class);

        // 3 设置map和reduce类
        job.setMapperClass(WcMapper.class);
        job.setReducerClass(WcReducer.class);

        // 4 设置map输出
        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(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 7 提交
        boolean result = job.waitForCompletion(true);

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