https://www.cnblogs.com/edisonchou/p/4297599.html
实例:
链接:https://pan.baidu.com/s/1qeryRGn2oyXeyLSqabKBBA
提取码:5wia
复制这段内容后打开百度网盘手机App,操作更方便哦
关键代码:
package com.example.demo.mapred;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Counter;
import org.apache.hadoop.mapreduce.Mapper;
import java.io.IOException;
public class WCMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//普通计数器
// Text keyOut = new Text();
// IntWritable valueOut = new IntWritable();
// String[] arr = value.toString().split(" ");
// for(String s : arr){
// keyOut.set(s);
// valueOut.set(1);
// context.write(keyOut,valueOut);
// }
// *******************************************************
// 自定义计数器
// 这里有两个形参,第一个是计数器组的名称,第二是计数器的名称。
Counter sensitiveCounter = context.getCounter("Sensitive Words:", "Hello");
String line = value.toString();
// 这里假定Hello是一个敏感词
if(line.contains("Hello")){
sensitiveCounter.increment(1L);
}
String[] spilted = line.split(" ");
for (String word : spilted) {
context.write(new Text(word), new IntWritable());
}
}
}