MapReduce之WordCount

用户统计文件中的单词出现的个数

注意各个文件的导包，job的封装步骤

WordCountMapper.java

package top.wintp.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;

/**
 * @description: description:
 * <p>
 * @author: upuptop
 * <p>
 * @qq: 337081267
 * <p>
 * @CSDN: http://blog.csdn.net/pyfysf
 * <p>
 * @cnblogs: http://www.cnblogs.com/upuptop
 * <p>
 * @blog: http://wintp.top
 * <p>
 * @email: pyfysf@163.com
 * <p>
 * @time: 2019/05/2019/5/21
 * <p>
 */
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    private Text K = new Text();
    private IntWritable V = 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) {
            K.set(word);
            context.write(K, V);
        }

    }
}

WordCountReduce

package top.wintp.mapreduce.wordcount;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

/**
 * @description: description:
 * <p>
 * @author: upuptop
 * <p>
 * @qq: 337081267
 * <p>
 * @CSDN: http://blog.csdn.net/pyfysf
 * <p>
 * @cnblogs: http://www.cnblogs.com/upuptop
 * <p>
 * @blog: http://wintp.top
 * <p>
 * @email: pyfysf@163.com
 * <p>
 * @time: 2019/05/2019/5/21
 * <p>
 */
public class WordCountReduce extends Reducer<Text, IntWritable, Text, IntWritable> {
    private IntWritable V = 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();
        }

        V.set(sum);
        context.write(key, V);
    }
}

WordCountRunner

package top.wintp.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 org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 * @description: description:
 * <p>
 * @author: upuptop
 * <p>
 * @qq: 337081267
 * <p>
 * @CSDN: http://blog.csdn.net/pyfysf
 * <p>
 * @cnblogs: http://www.cnblogs.com/upuptop
 * <p>
 * @blog: http://wintp.top
 * <p>
 * @email: pyfysf@163.com
 * <p>
 * @time: 2019/05/2019/5/21
 * <p>
 */
public class WordCountRunner implements Tool {
    private Configuration conf;

    public int run(String[] strings) throws Exception {
        //封装job
        Job job = Job.getInstance(this.conf);
        job.setJarByClass(WordCountRunner.class);

        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReduce.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job, new Path("E:/input/wordcount/"));
        FileOutputFormat.setOutputPath(job, new Path("E:/output/wordcount/" + System.currentTimeMillis()));

        //提交任务
        int result = job.waitForCompletion(true) ? 0 : 1;

        return result;
    }

    public void setConf(Configuration configuration) {
        this.conf = configuration;
    }

    public Configuration getConf() {
        return this.conf;
    }

    public static void main(String[] args) throws Exception {
        int status = ToolRunner.run(new WordCountRunner(), args);
        System.exit(status);
    }
}

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