一、问题描述
场景:有大量文件,里面存储了单词
任务:如何统计每个单词出现的次数?
二、数据格式
2.1 输入数据
hello tom
hello jerry
hello kitty
hello world
hello tom
2.2 输出格式
hello 5
jerry 1
kitty 1
tom 2
world 1
三、分析
step1 step2 step3
四、代码实现
WorldCount代码
package edu.jianwei.wc;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 WorldCount {
static class WCMapper extends
Mapper<LongWritable, Text, Text, LongWritable> {
@Override
protected void map(LongWritable key, Text value,
Mapper<LongWritable, Text, Text, LongWritable>.Context context)
throws IOException, InterruptedException {
String line = value.toString();
String[] words = line.split(" ");
for (String word : words) {
context.write(new Text(word), new LongWritable(1));
}
}
}
static class WCReduce extends
Reducer<Text, LongWritable, Text, LongWritable> {
@Override
protected void reduce(Text key, Iterable<LongWritable> v2s,
Reducer<Text, LongWritable, Text, LongWritable>.Context context)
throws IOException, InterruptedException {
long count = 0;
for (LongWritable v2 : v2s) {
count += v2.get();
}
context.write(key, new LongWritable(count));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(WorldCount.class);
job.setMapperClass(WCMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(LongWritable.class);
FileInputFormat.setInputPaths(job, new Path("/wc"));
job.setReducerClass(WCReduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
FileOutputFormat.setOutputPath(job, new Path("/wc/wcout"));
job.waitForCompletion(true);
}
}