package com.bjsxt;
import java.util.List;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.streaming.Durations;
import org.apache.spark.streaming.api.java.JavaDStream;
import org.apache.spark.streaming.api.java.JavaPairDStream;
import org.apache.spark.streaming.api.java.JavaReceiverInputDStream;
import org.apache.spark.streaming.api.java.JavaStreamingContext;
import com.google.common.base.Optional;
import scala.Tuple2;
import scala.actors.threadpool.Arrays;
public class UpdateStateByKeyOperator {
public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("test").setMaster("local[2]");
JavaStreamingContext jsc = new JavaStreamingContext(conf, Durations.seconds(5));
/**
* 去除日志的重复
*/
jsc.sparkContext().setLogLevel("ERROR");
/**
* 设置checkpoint目录: 多久会接收内存中的数据(每一个key所对应的状态)写入到磁盘上呢?
* 如果你的batchinterval小于10S,那么10S会将内存中的数据写入到磁盘一份
* 如果batchinterval大于10S,那么就以batchinterval为准 这样做是为了防止频繁的写HDFS
* 设置checkpoint目录的两种方式: 1.jsc.checkpoint("./checkpoint"); 2.JavaSparkContext
* sc=jsc.sparkContxt(); sc.setCheckpointDir("./checkpoint");
*
*/
jsc.checkpoint("./checkpoint");
/**
* 从Linux端接收数据
*/
JavaReceiverInputDStream<String> lines = jsc.socketTextStream("node01", 9999);
/**
* 调用flatmap算子进行切分
*/
JavaDStream<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
@Override
public Iterable<String> call(String s) throws Exception {
return Arrays.asList(s.split(" "));
}
});
/**
* 调用mapToPair 进行分类
*/
JavaPairDStream<String, Integer> ones = words.mapToPair(new PairFunction<String, String, Integer>() {
@Override
public Tuple2<String, Integer> call(String s) throws Exception {
return new Tuple2<String, Integer>(s, 1);
}
});
/**
* 调用updateStateByKey算子
*
*/
JavaPairDStream<String, Integer> counts = ones
.updateStateByKey(new Function2<List<Integer>, Optional<Integer>, Optional<Integer>>() {
@Override
public Optional<Integer> call(List<Integer> values, Optional<Integer> state) throws Exception {
/**
* values:经过分组最后 这个key所对应的value [1,1,1,1,1] state:这个key在本次之前之前的状态
*/
Integer updateValue = 0;
if (state.isPresent()) {
updateValue = state.get();
}
for (Integer value : values) {
updateValue += value;
}
return Optional.of(updateValue);
}
});
// output operator
counts.print();
jsc.start();
jsc.awaitTermination();
jsc.close();
}
}
SparkStreaming部分:updateStateByKey算子(包含从Linux端获取数据,flatmap切分,maptopair分类,写入到本地创建的文件夹中)【Java版纯代码】
最新推荐文章于 2020-11-09 18:53:49 发布