Flink 状态编程 广播状态（Broadcast State）案例

测试数据：

广播流测试数据：

java
scala
python

普通流测试数据：

java代码量太大
go是一种静态强类型、编译型、并发型，并具有垃圾回收功能的编程语言
scala流式处理语言，主要应用于大数据开发场景
php是web开发语言
php是web开发语言

package com.cnic.app;

import org.apache.flink.api.common.state.MapStateDescriptor;
import org.apache.flink.api.common.typeinfo.BasicTypeInfo;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.datastream.BroadcastStream;
import org.apache.flink.streaming.api.datastream.DataStream;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.co.BroadcastProcessFunction;
import org.apache.flink.util.Collector;

public class BroadcastTest01 {
    public static void main(String[] args) throws Exception {
        // TODO 1.创建执行环境
        StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        env.setParallelism(2);
        // TODO 2.读取数据构建数据源
        // 2.1读取数据构建广播流
        DataStreamSource<String> broadcastDs = env.socketTextStream("hadoop102", 9999);
        // 定义数据广播规则
        MapStateDescriptor<String, String> configFilter = new MapStateDescriptor<String, String>("configFilter", BasicTypeInfo.STRING_TYPE_INFO, BasicTypeInfo.STRING_TYPE_INFO);
        // 对数据进行广播
        BroadcastStream<String> broadcastConfig = broadcastDs.setParallelism(1).broadcast(configFilter);

        // 2.2读取数据构建常规流
        DataStreamSource<String> kafkaDs = env.socketTextStream("hadoop102", 8888);

        // TODO 3.对广播数据进行关联
        DataStream<String> resultDs = kafkaDs.connect(broadcastConfig).process(new BroadcastProcessFunction<String, String, String>() {
            //设置拦截的关键字
            private String keyWords = null;

            @Override
            public void open(Configuration parameters) throws Exception {
                super.open(parameters);
                keyWords = "java";
                System.out.println("初始化keyWords: " + keyWords);
            }

            //每条都会处理
            @Override
            public void processElement(String value, ReadOnlyContext readOnlyContext, Collector<String> out) throws Exception {
                if (value.contains(keyWords)) {
                    out.collect("拦截消息:" + value + ", 原因:包含拦截关键字：" + keyWords);
                }
            }

            //对广播变量获取更新
            @Override
            public void processBroadcastElement(String value, Context context, Collector<String> out) throws Exception {
                keyWords = value;
                System.out.println("更新关键字:" + value);
            }
        });

        // 打印测试
        resultDs.print("result");

        // TODO 启动任务
        env.execute("BroadcastTest");
    }
}