入门代码示例
flink 很好的支持了批流一体，那么在代码层面，其实只是在开始获取执行环境时有区别，剩下的处理逻辑基本相同，执行代码需要引入相关依赖，参考本文下方 pom的具体配置，详情如下
批处理代码
package com.lxs.flink.batch;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;
/**
* @author lixinsong
* @version version
* @desc
* @date 2020/11/04
*/
public class WordCount {
public static void main(String[] args) throws Exception {
// 获取批处理的执行环境
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
env.setParallelism(4);
DataSet<String> dataSet = env.readTextFile(
"D:\\study\\java\\workspace_song\\flink-learning\\src\\main\\resources\\wordcount.txt");
DataSet<Tuple2<String, Integer>> result = dataSet.flatMap(new MyFlatMapper())
.groupBy(0) // 按照第一个位置的word分组
.sum(1);// 将第二个位置的word求和
result.print();
}
public static class MyFlatMapper implements FlatMapFunction<String, Tuple2<String, Integer>> {
@Override
public void flatMap(String s, Collector<Tuple2<String, Integer>> collector) throws Exception {
String[] arr = s.split(" ");
for (String a: arr) {
collector.collect(new Tuple2<>(a, 1));
}
}
}
}
- 通过 ExecutionEnvironment.getExecutionEnvironment() 获取批处理的执行环境
- 通过 readTextFile 方法，读取磁盘上保存的某个文件，文件内容如下
hi li
hi xin
hi song
li xin song - 读取数据之后经过算子转换，最终输出
上述代码的执行结果为
image.png
流式处理
在流式处理中，需要输入数据源源不断，这里使用socket 流代替输入流
package com.lxs.flink.realtime;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.streaming.api.datastream.DataStreamSource;
import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
import org.apache.flink.util.Collector;
/**
* @author lixinsong
* @version version
* @desc
* @date 2020/11/24
*/
public class WordCount {
public static void main(String[] args) throws Exception {
StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
env.setParallelism(4); // 默认是执行机器的核数
DataStreamSource<String> input = env.socketTextStream("127.0.0.1", 8888);
input.flatMap(new FlatMapFunction<String, Tuple2<String, Integer>>() {
@Override
public void flatMap(String value, Collector<Tuple2<String, Integer>> out) throws Exception {
String[] s = value.split(" ");
for (String word : s) {
out.collect(Tuple2.of(word, 1));
}
}
// 流式处理是没有 group by 的
}).keyBy(0).sum(1).print();
// 流式处理必须启动执行
env.execute("word count test");
}
}
- 与批处理不同，流式处理需要使用 StreamExecutionEnvironment.getExecutionEnvironment() 获取执行环境
- 最后必须使用 env.execute 启动
在终端输入 nc -lk 8888 先输入 li xin
控制台输出
3> (li,1)
3> (xin,1)
继续在控制台输入 li xin , 结果输出为
3> (li,1)
3> (xin,1)
3> (li,2)
3> (xin,2)
pom 配置
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>frauddetection</groupId>
<artifactId>frauddetection</artifactId>
<version>0.1</version>
<packaging>jar</packaging>
<name>Flink Walkthrough DataStream Java</name>
<url>https://flink.apache.org</url>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<flink.version>1.11.2</flink.version>
<java.version>1.8</java.version>
<scala.binary.version>2.11</scala.binary.version>
<maven.compiler.source>${java.version}</maven.compiler.source>
<maven.compiler.target>${java.version}</maven.compiler.target>
<log4j.version>2.12.1</log4j.version>
<lombok.version>1.18.12</lombok.version>
</properties>
<repositories>
<repository>
<id>apache.snapshots</id>
<name>Apache Development Snapshot Repository</name>
<url>https://repository.apache.org/content/repositories/snapshots/</url>
<releases>
<enabled>false</enabled>
</releases>
<snapshots>
<enabled>true</enabled>
</snapshots>
</repository>
</repositories>
<dependencies>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-walkthrough-common_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-java</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-clients_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-slf4j-impl</artifactId>
<version>${log4j.version}</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-api</artifactId>
<version>${log4j.version}</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<version>${log4j.version}</version>
<scope>runtime</scope>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.flink/flink-connector-kafka-0.10 -->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-kafka_2.12</artifactId>
<version>1.11.2</version>
</dependency>
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>
<version>${lombok.version}</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.1</version>
<configuration>
<source>${java.version}</source>
<target>${java.version}</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>3.0.0</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<artifactSet>
<excludes>
<exclude>org.apache.flink:force-shading</exclude>
<exclude>com.google.code.findbugs:jsr305</exclude>
<exclude>org.slf4j:*</exclude>
<exclude>org.apache.logging.log4j:*</exclude>
</excludes>
</artifactSet>
<filters>
<filter>
<artifact>*:*</artifact>
<excludes>
<exclude>META-INF/*.SF</exclude>
<exclude>META-INF/*.DSA</exclude>
<exclude>META-INF/*.RSA</exclude>
</excludes>
</filter>
</filters>
<transformers>
<transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
<!-- 执行主类 -->
<mainClass>spendreport.FraudDetectionJob</mainClass>
</transformer>
</transformers>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
