原文地址:https://www.cnblogs.com/learn-bigdata/p/10794881.html
广播变量:主要应用与Driver创建的变量,在Executor端需要用到时,可以使用广播变量
package SparkStreaming;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.broadcast.Broadcast;
import java.util.Arrays;
import java.util.List;
public class BroadCast {
public static void main(String[] args) {
SparkConf conf = new SparkConf()
.setMaster("local")
.setAppName("BroadCastTest");
JavaSparkContext sc = new JavaSparkContext(conf);
/*
* 使用广播变量,广播变量的定义必须在driver端,因为sc没有被序列化不能被发送到Executor端
* */
Broadcast<String> blackname = sc.broadcast("dwj3");
List<String> name = Arrays.asList(
"dwj1",
"dwj2",
"dwj3");
//创建广播变量(创建广播变量的类型根据自己的需要)
//Broadcast<Map<String, Map<String, Object>>> labelLogicMapBroadCast = sc.broadcast(labelLogicMap);
//Broadcast<Map<String, Map<String, List<T_LabelSecondLogic>>>> labelSecondLogicMapBroadCast = sc.broadcast(labelSecondLogicMap);
//Broadcast<Map<String, Map<String, Object>>> hotCaculateMapBroadCast = sc.broadcast(hotCaculateMap);
//Broadcast<Map<String, Map>> importanceParameterMapBroadCast = sc.broadcast(importanceParameterMap);
//String blackName = "dwj3";
JavaRDD<String> nameRDD = sc.parallelize(name);
JavaRDD<String> namefilter = nameRDD.filter(new Function<String, Boolean>() {
@Override
public Boolean call(String s) throws Exception {
String blacknames = blackname.getValue();
return !blacknames.equals(s);
}
});
List<String> lastname = namefilter.collect();
for(String str:lastname){
System.out.println(str);
}
}
}