Flume拦截器

一、Flume拦截器

时间戳拦截器

Timestamp.conf

#1.定义agent名， source、channel、sink的名称
a4.sources = r1
a4.channels = c1
a4.sinks = k1

#2.具体定义source
a4.sources.r1.type = spooldir
a4.sources.r1.spoolDir = /opt/module/flume-1.8.0/upload

#定义拦截器，为文件最后添加时间戳
a4.sources.r1.interceptors = i1
a4.sources.r1.interceptors.i1.type = org.apache.flume.interceptor.TimestampInterceptor$Builder

#具体定义channel
a4.channels.c1.type = memory
a4.channels.c1.capacity = 10000
a4.channels.c1.transactionCapacity = 100


#具体定义sink
a4.sinks.k1.type = hdfs
a4.sinks.k1.hdfs.path = hdfs://bigdata111:9000/flume-interceptors/%H
a4.sinks.k1.hdfs.filePrefix = events-
a4.sinks.k1.hdfs.fileType = DataStream

#不按照条数生成文件
a4.sinks.k1.hdfs.rollCount = 0
#HDFS上的文件达到128M时生成一个文件
a4.sinks.k1.hdfs.rollSize = 134217728
#HDFS上的文件达到60秒生成一个文件
a4.sinks.k1.hdfs.rollInterval = 60

#组装source、channel、sink
a4.sources.r1.channels = c1
a4.sinks.k1.channel = c1

启动命令

/opt/module/flume-1.8.0/bin/flume-ng agent -n a4 \
-f /opt/module/flume-1.8.0/jobconf/flume-interceptors.conf \
-c /opt/module/flume-1.8.0/conf \
-Dflume.root.logger=INFO,console

主机名拦截器

Host.conf

#1.定义agent
a1.sources= r1
a1.sinks = k1
a1.channels = c1

#2.定义source
a1.sources.r1.type = exec
a1.sources.r1.channels = c1
a1.sources.r1.command = tail -F /opt/Andy
#拦截器
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = host

#参数为true时用IP192.168.1.111，参数为false时用主机名，默认为true
a1.sources.r1.interceptors.i1.useIP = false
a1.sources.r1.interceptors.i1.hostHeader = agentHost

 #3.定义sinks
a1.sinks.k1.type=hdfs
a1.sinks.k1.channel = c1
a1.sinks.k1.hdfs.path = hdfs://bigdata111:9000/flumehost/%H
a1.sinks.k1.hdfs.filePrefix = Andy_%{agentHost}
#往生成的文件加后缀名.log
a1.sinks.k1.hdfs.fileSuffix = .log
a1.sinks.k1.hdfs.fileType = DataStream
a1.sinks.k1.hdfs.writeFormat = Text
a1.sinks.k1.hdfs.rollInterval = 10
a1.sinks.k1.hdfs.useLocalTimeStamp = true
 
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
 
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

启动命令：

bin/flume-ng agent -c conf/ -f jobconf/host.conf -n a1 -Dflume.root.logger=INFO,console

UUID拦截器

uuid.conf

a1.sources = r1
a1.sinks = k1
a1.channels = c1

a1.sources.r1.type = exec
a1.sources.r1.channels = c1
a1.sources.r1.command = tail -F /opt/Andy
a1.sources.r1.interceptors = i1
#type的参数不能写成uuid，得写具体，否则找不到类
a1.sources.r1.interceptors.i1.type = org.apache.flume.sink.solr.morphline.UUIDInterceptor$Builder
#如果UUID头已经存在,它应该保存
a1.sources.r1.interceptors.i1.preserveExisting = true
a1.sources.r1.interceptors.i1.prefix = UUID_

#如果sink类型改为HDFS，那么在HDFS的文本中没有headers的信息数据
a1.sinks.k1.type = logger

a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
# bin/flume-ng agent -c conf/ -f jobconf/uuid.conf -n a1 -Dflume.root.logger==INFO,console

查询替换拦截器

search.conf

#1 agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

#2 source
a1.sources.r1.type = exec
a1.sources.r1.channels = c1
a1.sources.r1.command = tail -F /opt/Andy
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = search_replace

#遇到数字改成AncientMing，A123会替换为AAncientMing
a1.sources.r1.interceptors.i1.searchPattern = [0-9]+
a1.sources.r1.interceptors.i1.replaceString = AncientMing
a1.sources.r1.interceptors.i1.charset = UTF-8

#3 sink
a1.sinks.k1.type = logger

#4 Chanel
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

#5 bind
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
# bin/flume-ng agent -c conf/ -f jobconf/search.conf -n a1 -Dflume.root.logger=INFO,console

正则过滤拦截器

filter.conf

#1 agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

#2 source
a1.sources.r1.type = exec
a1.sources.r1.channels = c1
a1.sources.r1.command = tail -F /opt/Andy
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = regex_filter
a1.sources.r1.interceptors.i1.regex = ^A.*
#如果excludeEvents设为false,表示过滤掉不是以A开头的events。如果excludeEvents设为true，则表示过滤掉以A开头的events。
a1.sources.r1.interceptors.i1.excludeEvents = true

a1.sinks.k1.type = logger

a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
# bin/flume-ng agent -c conf/ -f jobconf/filter.conf -n a1 -Dflume.root.logger=INFO,console

正则抽取拦截器

extractor.conf

#1 agent
a1.sources = r1
a1.sinks = k1
a1.channels = c1

#2 source
a1.sources.r1.type = exec
a1.sources.r1.channels = c1
a1.sources.r1.command = tail -F /opt/Andy
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = regex_extractor
a1.sources.r1.interceptors.i1.regex = hostname is (.*?) ip is (.*)
a1.sources.r1.interceptors.i1.serializers = s1 s2
a1.sources.r1.interceptors.i1.serializers.s1.name = cookieid
a1.sources.r1.interceptors.i1.serializers.s2.name = ip

a1.sinks.k1.type = logger

a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1
# bin/flume-ng agent -c conf/ -f jobconf/extractor.conf -n a1 -Dflume.root.logger=INFO,console

注：正则抽取拦截器的headers不会出现在文件名和文件内容中

二、Flume自定义拦截器

字母小写变大写

1.Pom.xml

   <dependencies>
        <!-- flume核心依赖 -->
        <dependency>
            <groupId>org.apache.flume</groupId>
            <artifactId>flume-ng-core</artifactId>
            <version>1.8.0</version>
        </dependency>
    </dependencies>
    <build>
        <plugins>
            <!-- 打包插件 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-jar-plugin</artifactId>
                <version>2.4</version>
                <configuration>
                    <archive>
                        <manifest>
                            <addClasspath>true</addClasspath>
                            <classpathPrefix>lib/</classpathPrefix>
                            <mainClass></mainClass>
                        </manifest>
                    </archive>
                </configuration>
            </plugin>
            <!-- 编译插件 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>utf-8</encoding>
                </configuration>
            </plugin>
        </plugins>
    </build>

2.自定义实现拦截器

import org.apache.flume.Context;
import org.apache.flume.Event;
import org.apache.flume.interceptor.Interceptor;
 
import java.util.ArrayList;
import java.util.List;
 
public class MyInterceptor implements Interceptor {
    @Override
    public void initialize() {
    }
 
    @Override
    public void close() {
    }
 
    /**
     * 拦截source发送到通道channel中的消息
     *
     * @param event 接收过滤的event
     * @return event    根据业务处理后的event
     */
    @Override
    public Event intercept(Event event) {
        // 获取事件对象中的字节数据
        byte[] arr = event.getBody();
        // 将获取的数据转换成大写
        event.setBody(new String(arr).toUpperCase().getBytes());
        // 返回到消息中
        return event;
    }
    // 接收被过滤事件集合
    @Override
    public List<Event> intercept(List<Event> events) {
        List<Event> list = new ArrayList<>();
        for (Event event : events) {
            list.add(intercept(event));
        }
        return list;
    }
 
    public static class Builder implements Interceptor.Builder {
        // 获取配置文件的属性
        @Override
        public Interceptor build() {
            return new MyInterceptor();
        }
 
        @Override
        public void configure(Context context) {
 
        }
    }

使用Maven做成Jar包，在flume的目录下mkdir jar，上传此jar到jar目录中

Flume配置文件

ToUpCase.conf

#1.agent 
a1.sources = r1
a1.sinks =k1
a1.channels = c1
 
 
# Describe/configure the source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F /opt/Andy
a1.sources.r1.interceptors = i1
#全类名$Builder
a1.sources.r1.interceptors.i1.type = ToUpCase.MyInterceptor$Builder
 
# Describe the sink
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = /ToUpCase1
a1.sinks.k1.hdfs.filePrefix = events-
a1.sinks.k1.hdfs.round = true
a1.sinks.k1.hdfs.roundValue = 10
a1.sinks.k1.hdfs.roundUnit = minute
a1.sinks.k1.hdfs.rollInterval = 3
a1.sinks.k1.hdfs.rollSize = 20
a1.sinks.k1.hdfs.rollCount = 5
a1.sinks.k1.hdfs.batchSize = 1
a1.sinks.k1.hdfs.useLocalTimeStamp = true
#生成的文件类型，默认是 Sequencefile，可用 DataStream，则为普通文本
a1.sinks.k1.hdfs.fileType = DataStream
 
# Use a channel which buffers events in memory
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100
 
# Bind the source and sink to the channel
a1.sources.r1.channels = c1
a1.sinks.k1.channel = c1

运行命令：

bin/flume-ng agent -c conf/ -n a1 -f jar/ToUpCase.conf -C jar/Flume-1.0-SNAPSHOT.jar -Dflume.root.logger=DEBUG,console

三、Flume对接kafka

配置flume(flume-kafka.conf)

# define
a1.sources = r1
a1.sinks = k1
a1.channels = c1

# source
a1.sources.r1.type = exec
a1.sources.r1.command = tail -F -c +0 /opt/jars/calllog.csv
a1.sources.r1.shell = /bin/bash -c

# sink
a1.sinks.k1.type = org.apache.flume.sink.kafka.KafkaSink
a1.sinks.k1.brokerList = bigdata111:9092,bigdata112:9092,bigdata113:9092
a1.sinks.k1.topic = calllog
a1.sinks.k1.batchSize = 20
a1.sinks.k1.requiredAcks = 1

# channel
a1.channels.c1.type = memory
a1.channels.c1.capacity = 1000
a1.channels.c1.transactionCapacity = 100

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

进入flume根目录下，启动flume

/opt/module/flume-1.8.0/bin/flume-ng agent --conf /opt/module/flume-1.8.0/conf/ --name a1 --conf-file /opt/jars/flume2kafka.conf

四、kafka对接Flume

kafka2flume.conf

agent.sources = kafkaSource
agent.channels = memoryChannel
agent.sinks = hdfsSink

# The channel can be defined as follows.
agent.sources.kafkaSource.channels = memoryChannel
agent.sources.kafkaSource.type=org.apache.flume.source.kafka.KafkaSource
agent.sources.kafkaSource.zookeeperConnect=bigdata111:2181,bigdata112:2181,bigdata113:2181
agent.sources.kafkaSource.topic=calllog
#agent.sources.kafkaSource.groupId=flume
agent.sources.kafkaSource.kafka.consumer.timeout.ms=100


agent.channels.memoryChannel.type=memory
agent.channels.memoryChannel.capacity=10000
agent.channels.memoryChannel.transactionCapacity=1000
agent.channels.memoryChannel.type=memory
agent.channels.memoryChannel.capacity=10000
agent.channels.memoryChannel.transactionCapacity=1000


# the sink of hdfs
agent.sinks.hdfsSink.type=hdfs
agent.sinks.hdfsSink.channel = memoryChannel
agent.sinks.hdfsSink.hdfs.path=hdfs://bigdata111:9000/kafka2flume
agent.sinks.hdfsSink.hdfs.writeFormat=Text
agent.sinks.hdfsSink.hdfs.fileType=DataStream
#这两个不配置，会产生大量的小文件
agent.sinks.hdfsSink.hdfs.rollSize=0
agent.sinks.hdfsSink.hdfs.rollCount=0

启动命令

bin/flume-ng agent --conf conf --conf-file jobconf/kafka2flume.conf --name agent -Dflume.root.logger=INFO,console

注意：这个配置是从kafka过数据，但是需要重新向kafka的topic灌数据，他才会传到HDFS