flume拦截器-校验kafka消费的数据是否为json数据

首先我们在java中编写拦截器代码

这是pom文件导入的坐标

<?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.sias.gmall.flume.interceptor</groupId>
    <artifactId>flume-interceptor</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>19</maven.compiler.source>
        <maven.compiler.target>19</maven.compiler.target>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.apache.flume</groupId>
            <artifactId>flume-ng-core</artifactId>
            <version>1.9.0</version>
            <scope>provided</scope>
        </dependency>
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.62</version>
        </dependency>

    </dependencies>
    <build>
        <plugins>
            <plugin>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>2.3.2</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
            <plugin>
                <artifactId>maven-assembly-plugin</artifactId>
                <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>

编写校验json的代码 

public static boolean isJSONNValidate(String log){
        try {
            JSONObject.parseObject(log);
            return true;
        }catch (JSONException e){
            return false;
        }
    }

拦截器代码

package com.sias.gmall.flume.interceptor;/*
 *2023/4/29 15:35
 */

import com.sias.gmall.flume.interceptor.utils.JSONUtil;
import org.apache.flume.Context;
import org.apache.flume.Event;
import org.apache.flume.interceptor.Interceptor;

import java.nio.charset.StandardCharsets;
import java.util.Calendar;
import java.util.Iterator;
import java.util.List;

public class ETLInterceptor implements Interceptor {
    @Override
    public void initialize() {

    }

    @Override
    public Event intercept(Event event) {
        JSONUtil JSONUtil = new JSONUtil();
        //1、获取body当中的数据并转成字符串
        byte[] body = event.getBody();
        String log = new String(body, StandardCharsets.UTF_8);
        //2、判断字符串是否是一个合法的json，是：返回当前event；不是：返回null
        if (JSONUtil.isJSONNValidate(log)){
            return event;

        }else {
            return null;
        }

    }

    @Override
    public List<Event> intercept(List<Event> list) {
        Iterator<Event> iterator = list.iterator();
        while (iterator.hasNext()){
            //hasNext 判断有没有当前元素
            //next的左右有两个 一是获取当前元素，二是指针向后移动
            Event next = iterator.next();
            if(intercept(next)==null){
                iterator.remove();
            }
        }

        return list;
    }

    @Override
    public void close() {

    }
    public static class Builder implements Interceptor.Builder{

        @Override
        public Interceptor build() {
            return new ETLInterceptor();
        }

        @Override
        public void configure(Context context) {

        }
    }
}

然后对其进行打包 （先clean 在package）

上传到flume的lib文件夹下

编写flume/job/file_to_kafka.conf

a1.sources = r1
a1.sinks = k1
a1.channels = c1
# 2 配置 source
a1.sources.r1.type = TAILDIR
a1.sources.r1.filegroups = f1
a1.sources.r1.filegroups.f1 = /opt/module/applog/app.*
a1.sources.r1.positionFile = /opt/module/flume/taildir_position.json
#配置拦截器
a1.sources.r1.interceptors=i1
a1.sources.r1.interceptors.i1.type=com.sias.gmall.flume.interceptor.ETLInterceptor$Builder
# 3 配置 channel
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
# 4 配置 sink
a1.sinks.k1.type = org.apache.flume.sink.kafka.KafkaSink
a1.sinks.k1.kafka.bootstrap.servers = hadoop001:9092,hadoop002:9092,hadoop003:9092
a1.sinks.k1.kafka.topic = first
a1.sinks.k1.kafka.flumeBatchSize = 20
a1.sinks.k1.kafka.producer.acks = 1
a1.sinks.k1.kafka.producer.linger.ms = 1
# 5 拼接组件 
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

启动flume:

bin/flume-ng agent -n a1 -c conf/ -f job/file_to_kafka.conf -Dflume.root.logger=info,console

开启kafka的消费者 消费的主题是first，对应file_to_kafka.conf文件中的主题

bin/kafka-console-consumer.sh --bootstrap-server hadoop001:9092 --topic first

因为监控的是applog下的所有文件

此时我们在applog目录下的文件夹追加数据：

                如：echo "{a:1}">app.log

在消费端就能看见数据

如果我们写不是json的字符串：

                如 ：echo "{id">>app.log

那么消费端就不会有数据了，说明拦截成功了

最后我们紧接着在追加一个数据：echo "{id:4}">>app.log

就有可以在消费端看见数据了