pom.xml
<properties>
<flink.version>1.17.0</flink.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-java</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-clients</artifactId>
<version>${flink.version}</version>
</dependency>
</dependencies>
代码
流处理实现WordCount_无界流
读取 socket 文本流
在实际的生产环境中,真正的数据流其实是无界的,有开始却没有结束,这就要求我们需要持续地处理捕获的数据。为了模拟这种场景,可以监听 socket 端口,然后向该端口不断地发送数据。
[atguigu@node001 ~]$ sudo yum install -y netcat
[atguigu@node001 ~]$ nc -lk 7777
DataStream实现Wordcount:读socket(无界流)
package com.atguigu.wc;
import org.apache.flink.api.common.typeinfo.TypeHint;
import org.apache.flink.api.common.typeinfo.TypeInformation;
import org.apache.flink.api.common.typeinfo.Types;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.configuration.Configuration;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.datastream.SingleOutputStreamOperator;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;
/**
* TODO DataStream实现Wordcount:读socket(无界流)
*
*/
public class WordCountStreamUnboundedDemo {
public static void main(String[] args) throws Exception {
// TODO 1. 创建执行环境
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
// IDEA运行时,也可以看到webui,一般用于本地测试
// 需要引入一个依赖 flink-runtime-web
// 在idea运行,不指定并行度,默认就是 电脑的 线程数
// StreamExecutionEnvironment env = StreamExecutionEnvironment.createLocalEnvironmentWithWebUI(new Configuration());
env.setParallelism(3);
// TODO 2. 读取数据: socket
DataStreamSource<String> socketDS = env.socketTextStream("node001", 7777);
// TODO 3. 处理数据: 切换、转换、分组、聚合
SingleOutputStreamOperator<Tuple2<String, Integer>> sum = socketDS
.flatMap(
(String value, Collector<Tuple2<String, Integer>> out) -> {
String[] words = value.split(" ");
for (String word : words) {
out.collect(Tuple2.of(word, 1));
}
}
)
.setParallelism(2)
.returns(Types.TUPLE(Types.STRING, Types.INT))
// .returns(new TypeHint<Tuple2<String, Integer>>() {})
.keyBy(value -> value.f0)
.sum(1);
// TODO 4. 输出
sum.print();
// TODO 5. 执行
env.execute();
}
}
/**
* 并行度的优先级:
* 代码:算子 > 代码:env > 提交时指定 > 配置文件
*/
演示、对比