Flume采集App端埋点行为数据至Hdfs

vim file_to_kafka.conf

#定义组件
a1.sources = r1
a1.channels = c1

#配置source
a1.sources.r1.type = TAILDIR
a1.sources.r1.filegroups = f1
a1.sources.r1.filegroups.f1 = /opt/module/applog/log/app.*
a1.sources.r1.positionFile = /opt/module/flume/taildir_position.json

#配置channel
a1.channels.c1.type = org.apache.flume.channel.kafka.KafkaChannel
a1.channels.c1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092
a1.channels.c1.kafka.topic = topic_log
a1.channels.c1.parseAsFlumeEvent = false

#组装 
a1.sources.r1.channels = c1

# 创建脚本
vim f1.sh

#!/bin/bash

echo " --------启动 hadoop102 采集flume-------"
nohup /opt/module/flume/bin/flume-ng agent -n a1 -c /opt/module/flume/conf/ -f /opt/module/flume/job/file_to_kafka.conf >/dev/null 2>&1 &

# 增加权限
chmod 777 ./f1.sh

#定义组件
a1.sources=r1
a1.channels=c1
a1.sinks=k1

#配置source1
a1.sources.r1.type = org.apache.flume.source.kafka.KafkaSource
a1.sources.r1.batchSize = 5000
a1.sources.r1.batchDurationMillis = 2000
a1.sources.r1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.sources.r1.kafka.topics=topic_log
# 拦截器
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = org.example.TimestampInterceptor$Builder

#配置channel
a1.channels.c1.type = file
a1.channels.c1.checkpointDir = /opt/module/flume/checkpoint/behavior1
a1.channels.c1.dataDirs = /opt/module/flume/data/behavior1
a1.channels.c1.maxFileSize = 2146435071
a1.channels.c1.capacity = 1000000
a1.channels.c1.keep-alive = 6

#配置sink
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = /origin_data/gmall/log/topic_log/%Y-%m-%d
a1.sinks.k1.hdfs.filePrefix = log
a1.sinks.k1.hdfs.round = false


a1.sinks.k1.hdfs.rollInterval = 10
a1.sinks.k1.hdfs.rollSize = 134217728
a1.sinks.k1.hdfs.rollCount = 0

#控制输出文件类型
a1.sinks.k1.hdfs.fileType = CompressedStream
a1.sinks.k1.hdfs.codeC = gzip

#组装 
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

# 创建脚本
vim f2.sh

#!/bin/bash

echo " --------启动 hadoop102 日志数据flume-------"
nohup /opt/module/flume/bin/flume-ng agent -n a1 -c /opt/module/flume/conf -f /opt/module/flume/job/kafka_to_hdfs_log.conf >/dev/null 2>&1 &

# 增加权限
chmod 777 ./f2.sh

{
  "common": {
    "ar": "12",
    "ba": "realme",
    "ch": "wandoujia",
    "is_new": "1",
    "md": "realme Neo2",
    "mid": "mid_411",
    "os": "Android 13.0",
    "sid": "4f34596c-ca8f-434c-a8d5-356b944eb0d6",
    "vc": "v2.1.134"
  },
  "start": {
    "entry": "icon",
    "loading_time": 12974,
    "open_ad_id": 16,
    "open_ad_ms": 5415,
    "open_ad_skip_ms": 0
  },
  "ts": 1654620592548
}

<dependencies>
    <dependency>
        <groupId>org.apache.flume</groupId>
        <artifactId>flume-ng-core</artifactId>
        <version>1.10.1</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>

import com.alibaba.fastjson.JSONObject;
import org.apache.flume.Context;
import org.apache.flume.Event;
import org.apache.flume.interceptor.Interceptor;
import java.nio.charset.StandardCharsets;
import java.util.Iterator;

import java.util.List;
import java.util.Map;

public class TimestampInterceptor implements Interceptor {

    @Override
    public void initialize() {

    }

    @Override
    public Event intercept(Event event) {
    //1、获取header和body的数据
    Map<String, String> headers = event.getHeaders();
    String log = new String(event.getBody(), StandardCharsets.UTF_8);

    try {
        //2、将body的数据类型转成jsonObject类型（方便获取数据）
        JSONObject jsonObject = JSONObject.parseObject(log);

        //3、header中timestamp时间字段替换成日志生成的时间戳（解决数据漂移问题）
        String ts = jsonObject.getString("ts");
        headers.put("timestamp", ts);

        return event;
    } catch (Exception e) {
        e.printStackTrace();
        return null;
    }
}

@Override
public List<Event> intercept(List<Event> list) {
    Iterator<Event> iterator = list.iterator();
    while (iterator.hasNext()) {
        Event event = iterator.next();
        if (intercept(event) == null) {
            iterator.remove();
        }
    }
    return list;
}

    @Override
    public void close() {

    }

    public static class Builder implements Interceptor.Builder {
        @Override
        public Interceptor build() {
            return new TimestampInterceptor();
        }

        @Override
        public void configure(Context context) {
        }
    }
}

# 启动flume采集器
f1.sh
f2.sh

# 启动日志服务器
java -jar /opt/module/applog/gmall-remake-mock-2023-05-15-3.jar