package com.zhiyou.bd23;
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.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class WordCount {
//创建map类
public static class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
private Text outputKey = new Text();
private IntWritable outputValue = new IntWritable(1);
private String[] infos;
@Override
protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
infos = value.toString().split("\\s+");
for(String word:infos){
outputKey.set(word);
context.write(outputKey, outputValue);
}
}
}
//创建reduce类
public static class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{
private IntWritable outputValue = new IntWritable();
private int sum;
@Override
protected void reduce(Text key, Iterable<IntWritable> values,
Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
sum = 0;
for(IntWritable value:values){
sum += value.get();
}
outputValue.set(sum);
context.write(key, outputValue);
}
}
//创建main方法,配置并启动job
public static void main(String[] args) throws Exception {
Configuration configuration = new Configuration();
Job job = Job.getInstance(configuration);
job.setJarByClass(WordCount.class);
job.setJobName("hadoopwordcount");
job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
Path inputPath = new Path(args[0]);
Path outputPath = new Path(args[1]);
outputPath.getFileSystem(configuration).delete(outputPath, true);
FileInputFormat.addInputPath(job, inputPath);
FileOutputFormat.setOutputPath(job, outputPath);
System.exit(job.waitForCompletion(true)?0:1);
}
}
HADOOP统计出现的次数
最新推荐文章于 2024-09-18 10:39:18 发布