当前位置：首页 > news >正文

建立网站策划百度一下首页网页百度

news 2026/4/7 10:56:08

建立网站策划,百度一下首页网页百度,录音转文字网站开发,wordpress用户名在那个数据表1、什么是CEP？ Flink CEP即 Flink Complex Event Processing，是基于DataStream流式数据提供的一套复杂事件处理编程模型。你可以把他理解为基于无界流的一套正则匹配模型，即对于无界流中的各种数据(称为事件)，提供一种组合匹配的…

1、什么是CEP？

Flink CEP即 Flink Complex Event Processing，是基于DataStream流式数据提供的一套复杂事件处理编程模型。你可以把他理解为基于无界流的一套正则匹配模型，即对于无界流中的各种数据(称为事件)，提供一种组合匹配的功能。

在这里插入图片描述
上图中，以不同形状代表一个DataStream中不同属性的事件。以一个圆圈和一个三角组成一个Pattern后，就可以快速过滤出原来的DataStream中符合规律的数据。举个例子，比如很多网站需要对恶意登录的用户进行屏蔽，如果用户连续三次输入错误的密码，那就要锁定当前用户。在这个场景下，所有用户的登录行为就构成了一个无界的数据流DataStream。而连续三次登录失败就是一个匹配模型Pattern。CEP编程模型的功能就是从用户登录行为这个无界数据流DataStream中，找出符合这个匹配模Pattern的所有数据。这种场景下，使用我们前面介绍的各种DataStream API其实也是可以实现的，不过相对就麻烦很多。而CEP编程模型则提供了非常简单灵活的功能实现方式。

2、代码实现

2.1 引入maven依赖：

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"><modelVersion>4.0.0</modelVersion><groupId>com.roy</groupId><artifactId>FlinkDemo</artifactId><version>1.0</version><properties><flink.version>1.12.5</flink.version><maven.compiler.source>1.8</maven.compiler.source><maven.compiler.target>1.8</maven.compiler.target><log4j.version>2.12.1</log4j.version></properties><dependencies><dependency><groupId>org.apache.flink</groupId><artifactId>flink-java</artifactId><version>${flink.version}</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-clients_2.12</artifactId><version>${flink.version}</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-streaming-java_2.12</artifactId><version>${flink.version}</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-table-api-java-bridge_2.12</artifactId><version>${flink.version}</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-table-planner-blink_2.12</artifactId><version>${flink.version}</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-table-common</artifactId><version>${flink.version}</version></dependency><!-- CEP主要是下面这个依赖 --><dependency><groupId>org.apache.flink</groupId><artifactId>flink-cep_2.12</artifactId><version>${flink.version}</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-statebackend-rocksdb_2.12</artifactId><version>${flink.version}</version></dependency><dependency><groupId>org.apache.flink</groupId><artifactId>flink-shaded-hadoop-2-uber</artifactId><version>2.8.3-10.0</version></dependency><dependency><groupId>log4j</groupId><artifactId>log4j</artifactId><version>1.2.14</version></dependency></dependencies><build><plugins><plugin><groupId>org.apache.maven.plugins</groupId><artifactId>maven-assembly-plugin</artifactId><version>3.1.0</version><configuration><descriptorRefs><descriptorRef>jar-with-dependencies</descriptorRef></descriptorRefs></configuration><executions><execution><id>make-assembly</id><phase>package</phase><goals><goal>single</goal></goals></execution></executions></plugin></plugins></build></project>

2.2 基本流程

//1、获取原始事件流
DataStream<Event> input = ......; 
//2、定义匹配器
Pattern<Event,?> pattern = .......; 
//3、获取匹配流
PatternStream<Event> patternStream = CEP.pattern(input, pattern);
//4、将匹配流中的数据处理形成结果数据流
DataStream<Result> resultStream = patternStream.process(new PatternProcessFunction<Event, Result>() {@Overridepublic void processMatch(Map<String, List<Event>> pattern,Context ctx,Collector<Result> out) throws Exception {}
});

2.3 完整代码

注意：代码运行前，先启动2.4 nlk socket服务

package com.roy.flink.project.userlogin;import org.apache.flink.api.common.eventtime.SerializableTimestampAssigner;
import org.apache.flink.api.common.eventtime.WatermarkStrategy;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.cep.CEP;
import org.apache.flink.cep.PatternStream;
import org.apache.flink.cep.functions.PatternProcessFunction;
import org.apache.flink.cep.pattern.Pattern;
import org.apache.flink.cep.pattern.conditions.SimpleCondition;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.streaming.api.windowing.time.Time;
import org.apache.flink.util.Collector;import java.time.Duration;
import java.util.List;
import java.util.Map;/*** @desc 十秒内连续登录失败的用户分析。使用Flink CEP进行快速模式匹配*/
public class MyUserLoginAna {public static void main(String[] args) throws Exception {final StreamExecutionEnvironment env =StreamExecutionEnvironment.getExecutionEnvironment();// //BoundedOutOfOrdernessWatermarks定时提交Watermark的间隔env.getConfig().setAutoWatermarkInterval(1000L);// 使用Socket测试env.setParallelism(1);// 1、获取原始事件流（10.86.97.206改为实际地址）final DataStreamSource<String> dataStreamSource = env.socketTextStream("10.86.97.206",7777);final SingleOutputStreamOperator<UserLoginRecord> userLoginRecordStream = dataStreamSource.map(new MapFunction<String, UserLoginRecord>() {@Overridepublic UserLoginRecord map(String s) throws Exception {final String[] splitVal = s.split(",");return new UserLoginRecord(splitVal[0], Integer.parseInt(splitVal[1]), Long.parseLong(splitVal[2]));}}).assignTimestampsAndWatermarks(WatermarkStrategy.<UserLoginRecord>forBoundedOutOfOrderness(Duration.ofSeconds(1))// 主要针对乱序流，由于乱序流中需要等待迟到数据到齐，所以必须设置一个固定量的延迟时间.withTimestampAssigner((SerializableTimestampAssigner<UserLoginRecord>) (element, recordTimestamp) -> element.getLoginTime()));// 2、定义匹配器// 2.1：10秒内出现3次登录失败的记录（不一定连续）// Flink CEP定义消息匹配器。
//        final Pattern<UserLoginRecord, UserLoginRecord> pattern = Pattern.<UserLoginRecord>begin("start").where(new SimpleCondition<UserLoginRecord>() {
//            @Override
//            public boolean filter(UserLoginRecord userLoginRecord) throws Exception {
//                return 1 == userLoginRecord.getLoginRes();
//            }
//        }).times(3).within(Time.seconds(10));// 2.2：连续三次登录失败。next表示连续匹配。 不连续匹配使用followByfinal Pattern<UserLoginRecord, UserLoginRecord> pattern = Pattern.<UserLoginRecord>begin("one").where(new SimpleCondition<UserLoginRecord>() {@Overridepublic boolean filter(UserLoginRecord value) throws Exception {return 1 == value.getLoginRes();}}).next("two").where(new SimpleCondition<UserLoginRecord>() {@Overridepublic boolean filter(UserLoginRecord value) throws Exception {return 1 == value.getLoginRes();}}).next("three").where(new SimpleCondition<UserLoginRecord>() {@Overridepublic boolean filter(UserLoginRecord value) throws Exception {return 1 == value.getLoginRes();}}).within(Time.seconds(10));// 3、获取匹配流final PatternStream<UserLoginRecord> badUser = CEP.pattern(userLoginRecordStream, pattern);final MyProcessFunction myProcessFunction = new MyProcessFunction();// 4、将匹配流中的数据处理成结果数据流final SingleOutputStreamOperator<UserLoginRecord> badUserStream = badUser.process(myProcessFunction);badUserStream.print("badUser");env.execute("UserLoginAna");}// mainpublic static class MyProcessFunction extends PatternProcessFunction<UserLoginRecord,UserLoginRecord>{@Overridepublic void processMatch(Map<String, List<UserLoginRecord>> match, Context ctx, Collector<UserLoginRecord> out) throws Exception {// 针对2.1 连续3次登录失败
//            final List<UserLoginRecord> records = match.get("start");
//            for(UserLoginRecord record : records){
//                out.collect(record);
//            }// 针对2.2 非连续3次登录失败final List<UserLoginRecord> records = match.get("three");for(UserLoginRecord record : records){out.collect(record);}}// processMarch}// MyProcessFunction
}

UserLoginRecord对象，如下：


public class UserLoginRecord {private String userId;private int loginRes; // 0-成功， 1-失败private long loginTime;public UserLoginRecord() {}public UserLoginRecord(String userId, int loginRes, long loginTime) {this.userId = userId;this.loginRes = loginRes;this.loginTime = loginTime;}@Overridepublic String toString() {return "UserLoginRecord{" +"userId='" + userId + '\'' +", loginRes=" + loginRes +", loginTime=" + loginTime +'}';}public String getUserId() {return userId;}public void setUserId(String userId) {this.userId = userId;}public int getLoginRes() {return loginRes;}public void setLoginRes(int loginRes) {this.loginRes = loginRes;}public long getLoginTime() {return loginTime;}public void setLoginTime(long loginTime) {this.loginTime = loginTime;}
}