MapRecuce是hadoop中计算的阶段,MapRecuce又分为map阶段和reduce阶段,map进行切割,reduce进行计算。下面为Java实现MapReduce的wordcount的案例
pom.xml文件
<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>
要处理文件的内容
Map阶段
package com.an.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;
/**
* KEYIN:默认情况下,是mr框架所读到的一行文本的起始偏移量,Long,在hadoop中有自己的更精简的序列化接口,所以不直接用Long,而是用LongWritable
* VALUEIN:默认情况下,是mr框架所读到的一行文本内容,String;此处用Text
* KEYOUT:是用户自定义逻辑处理完成之后输出数据中的key,在此处是单词,String;此处用Text
* VALUEOUT,是用户自定义逻辑处理完成之后输出数据中的value,在此处是单词次数,Integer,此处用IntWritable
* @author Administrator
*/
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
Text k = new Text();
IntWritable v = new IntWritable(1);
/**
* map阶段的业务逻辑就写在自定义的map()方法中
* maptask会对每一行输入数据调用一次我们自定义的map()方法
*/
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
// 1 将maptask传给我们的文本内容先转换成String
String line = value.toString();
// 2 根据空格将这一行切分成单词
String[] words = line.split(" ");
// 3 将单词输出为<单词,1>
for (String word : words) {
// 将单词作为key,将次数1作为value,以便于后续的数据分发,可以根据单词分发,以便于相同单词会到相同的reducetask中
k.set(word);
context.write(k, v);
}
}
}
reduce阶段
package com.an.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.Reducer;
/**
* KEYIN , VALUEIN 对应mapper输出的KEYOUT, VALUEOUT类型
* KEYOUT,VALUEOUT 对应自定义reduce逻辑处理结果的输出数据类型 KEYOUT是单词 VALUEOUT是总次数
* @author Administrator
*/
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
IntWritable v = new IntWritable();
/**
* key,是一组相同单词kv对的key
*/
protected void reduce(Text key, Iterable<IntWritable> values,
Context context) throws IOException, InterruptedException {
int sum = 0;
// 1 汇总各个key的个数
for (IntWritable value : values) {
sum+=value.get();
}
v.set(sum);
// 2输出该key的总次数
context.write(key,v);
}
}
driver阶段
package com.an.mapreduce;
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 {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(WordCountDriver.class);
job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.setInputPaths(job,new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean flag = job.waitForCompletion(true);
System.exit(flag?1:0);
}
}
在driver的main方法中用参数用运行,input.txt为要处理的文件,output是输出文件的位置。
输出的结果
查看part-r-00000,处理的结果