需求

• 定义两个拦截器，一个用于过滤不合法数据，一个用于区分日志类型。
• ETL拦截器主要用于，过滤时间戳不合法和Json数据不完整的日志。
• 日志类型区分拦截器主要用于，将启动日志和事件日志区分开来，方便发往Kafka的不同Topic。

导入依赖

	<dependencies>
        <dependency>
            <groupId>org.apache.flume</groupId>
            <artifactId>flume-ng-core</artifactId>
            <version>1.9.0</version>
        </dependency>
    </dependencies>

ETL拦截器

package com.aura.flume.interceptor;

import org.apache.flume.Context;
import org.apache.flume.Event;
import org.apache.flume.interceptor.Interceptor;

import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.List;

public class LogETLInterceptor implements Interceptor {

    @Override
    public void initialize() {

    }

    @Override
    public Event intercept(Event event) {

        // 1 获取数据
        byte[] body = event.getBody();
        String log = new String(body, Charset.forName("UTF-8"));

        // 2 判断数据类型并向Header中赋值
        if (log.contains("start")) {
            if (LogUtils.validateStart(log)){
                return event;
            }
        }else {
            if (LogUtils.validateEvent(log)){
                return event;
            }
        }

        // 3 返回校验结果
        return null;
    }

    @Override
    public List<Event> intercept(List<Event> events) {

        ArrayList<Event> interceptors = new ArrayList<>();

        for (Event event : events) {
            Event intercept1 = intercept(event);

            if (intercept1 != null){
                interceptors.add(intercept1);
            }
        }

        return interceptors;
    }

    @Override
    public void close() {

    }

    public static class Builder implements Interceptor.Builder{

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

        @Override
        public void configure(Context context) {

        }
    }
}

LogUtils工具类

package com.aura.flume.interceptor;
import org.apache.commons.lang.math.NumberUtils;

public class LogUtils {

    public static boolean validateEvent(String log) {
        // 服务器时间 | json
        // 1549696569054 | {"cm":{"ln":"-89.2","sv":"V2.0.4","os":"8.2.0","g":"M67B4QYU@gmail.com","nw":"4G","l":"en","vc":"18","hw":"1080*1920","ar":"MX","uid":"u8678","t":"1549679122062","la":"-27.4","md":"sumsung-12","vn":"1.1.3","ba":"Sumsung","sr":"Y"},"ap":"weather","et":[]}

        // 1 切割
        String[] logContents = log.split("\\|");

        // 2 校验
        if(logContents.length != 2){
            return false;
        }

        //3 校验服务器时间
        if (logContents[0].length()!=13 || !NumberUtils.isDigits(logContents[0])){
            return false;
        }

        // 4 校验json
        if (!logContents[1].trim().startsWith("{") || !logContents[1].trim().endsWith("}")){
            return false;
        }

        return true;
    }

    public static boolean validateStart(String log) {
        // {"action":"1","ar":"MX","ba":"HTC","detail":"542","en":"start","entry":"2","extend1":"","g":"S3HQ7LKM@gmail.com","hw":"640*960","l":"en","la":"-43.4","ln":"-98.3","loading_time":"10","md":"HTC-5","mid":"993","nw":"WIFI","open_ad_type":"1","os":"8.2.1","sr":"D","sv":"V2.9.0","t":"1559551922019","uid":"993","vc":"0","vn":"1.1.5"}

        if (log == null){
            return false;
        }

        // 校验json
        if (!log.trim().startsWith("{") || !log.trim().endsWith("}")){
            return false;
        }

        return true;
    }
}

日志类型拦截器

package com.aura.flume.interceptor;

import org.apache.flume.Context;
import org.apache.flume.Event;
import org.apache.flume.interceptor.Interceptor;

import java.nio.charset.Charset;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;

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

    }

    @Override
    public Event intercept(Event event) {

        // 区分日志类型：   body  header
        // 1 获取body数据
        byte[] body = event.getBody();
        String log = new String(body, Charset.forName("UTF-8"));

        // 2 获取header
        Map<String, String> headers = event.getHeaders();

        // 3 判断数据类型并向Header中赋值
        if (log.contains("start")) {
            headers.put("topic","topic_start");
        }else {
            headers.put("topic","topic_event");
        }

        return event;
    }

    @Override
    public List<Event> intercept(List<Event> events) {

        ArrayList<Event> interceptors = new ArrayList<>();

        for (Event event : events) {
            Event intercept1 = intercept(event);

            interceptors.add(intercept1);
        }

        return interceptors;
    }

    @Override
    public void close() {

    }

    public static class Builder implements  Interceptor.Builder{

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

        @Override
        public void configure(Context context) {

        }
    }
}

Flume配置文件

#从指定目录加载日志文件，到kafka channel，kafka channel有两个，一个保存启动日志，一个保存行为日志

# 指定source、channel
a1.sources = r1
a1.channels = c1 c2

# 配置source
a1.sources.r1.type = TAILDIR
a1.sources.r1.channels = c1 c2
# 断点续传索引文件
a1.sources.r1.positionFile = /opt/module/flume/test/log_position.json
a1.sources.r1.filegroups = f1
a1.sources.r1.filegroups.f1 = /tmp/logs/app.+
a1.sources.r1.fileHeader = true
a1.sources.ri.maxBatchCount = 200

# 配置拦截器
a1.sources.r1.interceptors = i1 i2
a1.sources.r1.interceptors.i1.type = com.aura.flume.interceptor.LogETLInterceptor$Builder
a1.sources.r1.interceptors.i2.type = com.aura.flume.interceptor.LogTypeInterceptor$Builder

# 选择器
a1.sources.r1.selector.type = multiplexing
a1.sources.r1.selector.header = topic
# 指定topic名字
a1.sources.r1.selector.mapping.topic_start = c1
a1.sources.r1.selector.mapping.topic_event = c2

# 配置channel
a1.channels.c1.type = org.apache.flume.channel.kafka.KafkaChannel
a1.channels.c1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.channels.c1.kafka.topic = topic_start
# 不包含flume headers信息
a1.channels.c1.parseAsFlumeEvent = false
a1.channels.c1.kafka.consumer.group.id = flume-consumer

a1.channels.c2.type = org.apache.flume.channel.kafka.KafkaChannel
a1.channels.c2.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.channels.c2.kafka.topic = topic_event
a1.channels.c1.parseAsFlumeEvent = false
a1.channels.c2.kafka.consumer.group.id = flume-consumer