Flink简单的统计异常数据，写入到redis里面。

最新推荐文章于 2025-05-30 16:56:16 发布

原创

最新推荐文章于 2025-05-30 16:56:16 发布 · 1.5k 阅读

2 ·

CC 4.0 BY-SA版权

本文介绍如何利用Apache Flink进行实时数据流处理，监测并统计异常数据，然后将这些异常数据有效地写入Redis缓存系统中，以便后续分析和快速查询。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

package com.coder.flink.core.aaa_spark;


import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONObject;
import org.apache.flink.api.common.functions.FilterFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.common.functions.RichMapFunction;
import org.apache.flink.api.common.serialization.SimpleStringSchema;
import org.apache.flink.api.common.state.ListState;
import org.apache.flink.api.common.state.ListStateDescriptor;
import org.apache.flink.api.common.state.ValueState;
import org.apache.flink.api.common.state.ValueStateDescriptor;
import org.apache.flink.api.java.functions.KeySelector;

 
import org.apache.flink.api.java.utils.ParameterTool;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.TimeCharacteristic;
import org.apache.flink.streaming.api.datastream.DataStream;

 
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.functions.sink.RichSinkFunction;
import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer010;
 
import redis.clients.jedis.Jedis;
import redis.clients.jedis.JedisPool;
import redis.clients.jedis.JedisPoolConfig;

import java.util.Properties;

/**
 * 统计kafka 的数据
 */
public class StormTimeCount {
    public static void main(String[] args) {
        final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
        //todo 获取kafka的配置属性
        args = new String[]{"--input-topic", "wxgz_dianyou_topic", "--bootstrap.servers", "node2.hadoop:9091,node3.hadoop:9091",
                "--zookeeper.connect", "node1.hadoop:2181,node2.hadoop:2181,node3.hadoop:2181", "--group.id", "cc1"};

        ParameterTool parameterTool = ParameterTool.fromArgs(args);

        env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);
        Properties pros = parameterTool.getProperties();
//        //todo 指定输入数据为kafka topic
        DataStream<String> kafkaDstream = env.addSource(new FlinkKafkaConsumer010<String>(
                        "wxgz_dianyou_topic",
//                "dianyou_filter",
                        new SimpleStringSchema(),
//                pros).setStartFromEarliest()
                        pros).setStartFromLatest()

        ).setParallelism(6);
        //todo 拿到字段统计 
        DataStream<JSONObject> logDstream = kafkaDstream.filter(new FilterFunction<String>() {
            @Override
            public boolean filter(String value) throws Exception {
                JSONObject logJson = JSON.parseObject(value);
                if (!logJson.containsKey("nginx_storm")) {
                    return f