Flink消费kafka消息实战

| git仓库地址(ssh) | git@github.com:zq2599/blog_demos.git | 该项目源码的仓库地址，ssh协议 |

这个git项目中有多个文件夹，本章源码在flinkkafkademo这个文件夹下，如下图红框所示：

开发Flink应用，部署到机器192.168.1.102

1. Flink环境搭建请参考《Flink1.7从安装到体验》；

2. 应用基本代码是通过mvn命令创建的，在命令行输入以下命令：

mvn archetype:generate -DarchetypeGroupId=org.apache.flink -DarchetypeArtifactId=flink-quickstart-java -DarchetypeVersion=1.7.0

根据提示，输入groupId为com.bolingcavalry，artifactId为flinkkafkademo，其他的直接按下回车键即可使用默认值，这样就得到了一个maven工程：flinkkafkademo；

3. 打开工程的pom.xml文件，增加以下两个依赖：

org.apache.flink

flink-connector-kafka-0.11_2.12

${flink.version}

com.alibaba

fastjson

1.2.28

4. 新增一个辅助类，用于将kafka消息中的内容转换成java对象：

/**

• @Description: 解析原始消息的辅助类

• @author: willzhao E-mail: zq2599@gmail.com

• @date: 2019/1/1 20:13

*/

public class JSONHelper {

/**

• 解析消息，得到时间字段

• @param raw

• @return

*/

public static long getTimeLongFromRawMessage(String raw){

SingleMessage singleMessage = parse(raw);

return null==singleMessage ? 0L : singleMessage.getTimeLong();

}

/**

• 将消息解析成对象

• @param raw

• @return

*/

public static SingleMessage parse(String raw){

SingleMessage singleMessage = null;

if (raw != null) {

singleMessage = JSONObject.parseObject(raw, SingleMessage.class);

}

return singleMessage;

}

}

5. SingleMessage对象的定义：

public class SingleMessage {

private long timeLong;

private String name;

private String bizID;

private String time;

private String message;

public long getTimeLong() {

return timeLong;

}

public void setTimeLong(long timeLong) {

this.timeLong = timeLong;

}

public String getName() {

return name;

}

public void setName(String name) {

this.name = name;

}

public String getBizID() {

return bizID;

}

public void setBizID(String bizID) {

this.bizID = bizID;

}

public String getTime() {

return time;

}

public void setTime(String time) {

this.time = time;

}

public String getMessage() {

return message;

}

public void setMessage(String message) {

this.message = message;

}

}

6. 实时处理的操作都集中在StreamingJob类，源码的关键位置已经加了注释，就不再赘述了：

/*

• Licensed to the Apache Software Foundation (ASF) under one

• or more contributor license agreements. See the NOTICE file

• distributed with this work for additional information

• regarding copyright ownership. The ASF licenses this file

• to you under the Apache License, Version 2.0 (the

• “License”); you may not use this file except in compliance

• with the License. You may obtain a copy of the License at

• http://www.apache.org/licenses/LICENSE-2.0
  

• Unless required by applicable law or agreed to in writing, software

• distributed under the License is distributed on an “AS IS” BASIS,

• WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

• See the License for the specific language governing permissions and

• limitations under the License.

*/

package com.bolingcavalry;

import org.apache.flink.api.common.functions.FlatMapFunction;

import org.apache.flink.api.common.serialization.SimpleStringSchema;

import org.apache.flink.api.java.tuple.Tuple;

import org.apache.flink.api.java.tuple.Tuple2;

import org.apache.flink.streaming.api.TimeCharacteristic;

import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;

import org.apache.flink.streaming.api.functions.AssignerWithPunctuatedWatermarks;

import org.apache.flink.streaming.api.functions.windowing.WindowFunction;

import org.apache.flink.streaming.api.watermark.Watermark;

import org.apache.flink.streaming.api.windowing.time.Time;

import org.apache.flink.streaming.api.windowing.windows.TimeWindow;

import org.apache.flink.streaming.connectors.kafka.FlinkKafkaConsumer011;

import javax.annotation.Nullable;

import java.util.Properties;

/**

• Skeleton for a Flink Streaming Job.

• For a tutorial how to write a Flink streaming application, check the

• tutorials and examples on the Flink Website.

• To package your application into a JAR file for execution, run

• ‘mvn clean package’ on the command line.

• If you change the name of the main class (with the public static void main(String[] args))

• method, change the respective entry in the POM.xml file (simply search for ‘mainClass’).

*/

public class StreamingJob {

public static void main(String[] args) throws Exception {

final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();

env.enableCheckpointing(5000); // 要设置启动检查点

env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime);

Properties props = new Properties();

props.setProperty(“bootstrap.servers”, “kafka1:9092”);

props.setProperty(“group.id”, “flink-group”);

//数据源配置，是一个kafka消息的消费者

FlinkKafkaConsumer011 consumer =

new FlinkKafkaConsumer011<>(“topic001”, new SimpleStringSchema(), props);

//增加时间水位设置类

consumer.assignTimestampsAndWatermarks(new AssignerWithPunctuatedWatermarks (){

@Override

public long extractTimestamp(String element, long previousElementTimestamp) {

return JSONHelper.getTimeLongFromRawMessage(element);

}

@Nullable

@Override

public Watermark checkAndGetNextWatermark(String lastElement, long extractedTimestamp) {

if (lastElement != null) {

return new Watermark(JSONHelper.getTimeLongFromRawMessage(lastElement));

}

return null;

}

});

env.addSource(consumer)

//将原始消息转成Tuple2对象，保留用户名称和访问次数(每个消息访问次数为1)

.flatMap((FlatMapFunction<String, Tuple2<String, Long>>) (s, collector) -> {

SingleMessage singleMessage = JSONHelper.parse(s);

if (null != singleMessage) {

collector.collect(new Tuple2<>(singleMessage.getName(), 1L));

}

})

//以用户名为key

.keyBy(0)

//时间窗口为2秒

.timeWindow(Time.seconds(2))

//将每个用户访问次数累加起来

.apply((WindowFunction<Tuple2<String, Long>, Tuple2<String, Long>, Tuple, TimeWindow>) (tuple, window, input, out) -> {

long sum = 0L;

for (Tuple2<String, Long> record: input) {

sum += record.f1;

}

Tuple2<String, Long> result = input.iterator().next();

result.f1 = sum;

out.collect(result);

})

//输出方式是STDOUT

.print();

env.execute(“Flink-Kafka demo”);

}

}

7. 在pom.xml所在文件夹执行以下命令打包：

mvn clean package -Dmaven.test.skip=true -U

8. 打包成功后，会在target目录下生成文件flinkkafkademo-1.0-SNAPSHOT.jar，将此文件提交到Flinkserver上，如下图：

9. 点击下图红框中的"Upload"按钮：

10. 如下图，选中刚刚上传的文件，填写类名，再点击"Submit"按钮即可启动Job：

11. 如下图，在Overview页面可见正在运行的任务：

现在所有服务都准备完毕，可以生产消息验证了；