大数据的核心是分布式存储HDFS和分布式计算MapReduce!
其中分布式计算MapReduce最基础实例Wordcount如下所示:
依赖jar包
$HADOOP_HOME/share/hadoop/common
$HADOOP_HOME/share/hadoop/common/lib
$HADOOP_HOME/share/hadoop/mapreduce
$HADOOP_HOME/share/hadoop/mapreducel/lib
1.WordCountMapper.java代码段:
package wc;
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;
// 泛型 k1 v1 k2 v2
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
@Override
protected void map(LongWritable key1, Text value1, Context context)
throws IOException, InterruptedException {
/*
* context 表示Mapper的上下文
* 上文:HDFS
* 下文:Mapper
*/
//数据: I love Beijing
String data = value1.toString();
//分词
String[] words = data.split(" ");
//输出 k2 v2
for(String w:words){
context.write(new Text(w), new IntWritable(1));
}
}
}
2.WordCountReducer.java代码段:
package wc;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
// k3 v3 k4 v4
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
@Override
protected void reduce(Text k3, Iterable<IntWritable> v3,Context context) throws IOException, InterruptedException {
/*
* context是reduce的上下文
* 上文
* 下文
*/
//对v3求和
int total = 0;
for(IntWritable v:v3){
total += v.get();
}
//输出 k4 单词 v4 频率
context.write(k3, new IntWritable(total));
}
}
3.WordCountMain.java代码段:
package wc;
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 WordCountMain {
public static void main(String[] args) throws Exception {
// 创建一个job和任务入口
Job job = Job.getInstance(new Configuration());
job.setJarByClass(WordCountMain.class); //main方法所在的class
//指定job的mapper和输出的类型<k2 v2>
job.setMapperClass(WordCountMapper.class);
job.setMapOutputKeyClass(Text.class); //k2的类型
job.setMapOutputValueClass(IntWritable.class); //v2的类型
//指定job的reducer和输出的类型<k4 v4>
job.setReducerClass(WordCountReducer.class);
job.setOutputKeyClass(Text.class); //k4的类型
job.setOutputValueClass(IntWritable.class); //v4的类型
//指定job的输入和输出
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//执行job
job.waitForCompletion(true);
}
}