尚硅谷大數(shù)據(jù)技術(shù)之Hadoop（MapReduce）（新）第1章 MapReduce概述

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.atguigu.mapreduce;

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;

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, Context context) throws IOException, InterruptedException {

// 1 獲取一行

String line = value.toString();

// 2 切割

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

// 3 輸出

for (String word : words) {

k.set(word);

context.write(k, v);

}

}

}

package com.atguigu.mapreduce.wordcount;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Reducer;

public class WordcountReducer 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 輸出

???????v.set(sum);

context.write(key,v);

}

}

package com.atguigu.mapreduce.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;

public class WordcountDriver {

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

// 1 獲取配置信息以及封裝任務(wù)

Configuration configuration = new Configuration();

Job job = Job.getInstance(configuration);

// 2 設(shè)置jar加載路徑

job.setJarByClass(WordcountDriver.class);

// 3 設(shè)置map和reduce類

job.setMapperClass(WordcountMapper.class);

job.setReducerClass(WordcountReducer.class);

// 4 設(shè)置map輸出

job.setMapOutputKeyClass(Text.class);

job.setMapOutputValueClass(IntWritable.class);

// 5 設(shè)置最終輸出kv類型

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(IntWritable.class);

// 6 設(shè)置輸入和輸出路徑

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);

}

}