+、版本
版本很重要
flink-1.11.3-bin-scala_2.11_recommend.tgz
+、配置 conf/flink-conf.yaml
1、web工作台
rest.address: 0.0.0.0
rest.port: 8081
2、集群
jobmanager.rpc.address: 0.0.0.0
jobmanager.rpc.port: 6123
+、启动/关闭
./start_cluster.sh
./stop_cluster.sh
+、防火墙
sudo ufw enable
sudo ufw status
sudo ufw allow 8081
+、DataStream
DataStream WordCount
问题1:使用 netcat 命令启动一个端口
windows环境下:nc -lk 9000要改为nc -L -v -p 9000
问题2:尽量使用Java原生的函数,不要过多使用lambda
因为可能会无法判断某个参数的类型,比如Collector
问题3: Connection refused: connect,连接拒绝
添加上.keyBy().timeWindow().reduce()函数之导致的
+、POM
<?xml version="1.0" encoding="UTF-8"?>
<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>com.office</groupId>
<artifactId>bigdata-flink-engine</artifactId>
<packaging>pom</packaging>
<version>1.0-SNAPSHOT</version>
<modules>
<module>flink-engine-demo</module>
<module>flink-engine-sku</module>
</modules>
<properties>
<encoding>UTF-8</encoding>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<java.version>1.8</java.version>
<scala.version>2.11</scala.version>
<scala.binary.version>2.11</scala.binary.version>
<flink.version>1.11.3</flink.version>
<maven.version>3.6.1</maven.version>
<maven.compiler.source>${java.version}</maven.compiler.source>
<maven.compiler.target>${java.version}</maven.compiler.target>
</properties>
<repositories>
<repository>
<id>spring</id>
<url>https://maven.aliyun.com/repository/public</url>
<releases>
<enabled>true</enabled>
</releases>
<snapshots>
<enabled>true</enabled>
</snapshots>
</repository>
<repository>
<id>apache</id>
<url>https://repository.apache.org/content/repositories/snapshots/</url>
</repository>
<repository>
<id>cloudera</id>
<url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
</repository>
</repositories>
<dependencies>
<!-- flink 的依赖项,不应该打包到JRA文件中 -->
<!-- These dependencies are provided, because they should not be packaged into the JAR file. -->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-java</artifactId>
<version>${flink.version}</version>
<scope>sources</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<scope>sources</scope>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-runtime-web_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
<scope>sources</scope>
</dependency>
<!-- 执行计划 -->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-table-planner-blink_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-table-common</artifactId>
<version>${flink.version}</version>
</dependency>
<!-- flink连接器-->
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-kafka_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-sql-connector-kafka_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-jdbc_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-csv</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-json</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.bahir</groupId>
<artifactId>flink-connector-redis_${scala.binary.version}</artifactId>
<version>1.0</version>
<exclusions>
<exclusion>
<artifactId>flink-streaming-java_${scala.binary.version}</artifactId>
<groupId>org.apache.flink</groupId>
</exclusion>
<exclusion>
<artifactId>flink-runtime_${scala.binary.version}</artifactId>
<groupId>org.apache.flink</groupId>
</exclusion>
<exclusion>
<artifactId>flink-core</artifactId>
<groupId>org.apache.flink</groupId>
</exclusion>
<exclusion>
<artifactId>flink-java</artifactId>
<groupId>org.apache.flink</groupId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-connector-hive_${scala.binary.version}</artifactId>
<version>${flink.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-metastore</artifactId>
<version>2.1.0</version>
</dependency>
<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-exec</artifactId>
<version>2.1.0</version>
</dependency>
<dependency>
<groupId>org.apache.flink</groupId>
<artifactId>flink-shaded-hadoop-2-uber</artifactId>
<version>2.7.5-10.0</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>2.1.0</version>
</dependency>
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.38</version>
<!--<version>8.0.20</version>-->
</dependency>
<!-- 高性能异步组件:Vertx-->
<dependency>
<groupId>io.vertx</groupId>
<artifactId>vertx-core</artifactId>
<version>3.9.0</version>
</dependency>
<dependency>
<groupId>io.vertx</groupId>
<artifactId>vertx-jdbc-client</artifactId>
<version>3.9.0</version>
</dependency>
<dependency>
<groupId>io.vertx</groupId>
<artifactId>vertx-redis-client</artifactId>
<version>3.9.0</version>
</dependency>
<!-- 日志 -->
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
<version>1.7.9</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<version>1.2.17</version>
<scope>runtime</scope>
</dependency>
<!-- fastjson -->
<dependency>
<groupId>com.alibaba</groupId>
<artifactId>fastjson</artifactId>
<version>1.2.70</version>
</dependency>
<!-- lombok -->
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>
<version>1.18.2</version>
<scope>provided</scope>
</dependency>
<!-- 工具库 -->
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-collections4</artifactId>
<version>4.4</version>
</dependency>
<dependency>
<groupId>org.apache.thrift</groupId>
<artifactId>libfb303</artifactId>
<version>0.9.3</version>
<type>pom</type>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
<version>28.2-jre</version>
</dependency>
</dependencies>
<build>
<plugins>
<!-- 编译插件 -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.5.1</version>
<configuration>
<source>${java.version}</source>
<target>${java.version}</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.18.1</version>
<configuration>
<useFile>false</useFile>
<disableXmlReport>true</disableXmlReport>
<includes>
<include>**/*Test.*</include>
<include>**/*Suite.*</include>
</includes>
</configuration>
</plugin>
<!-- 打包插件(会包含所有依赖) -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>2.3</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<filters>
<filter>
<artifact>*:*</artifact>
<excludes>
<!-- zip -d learn_spark.jar META-INF/*.RSA META-INF/*.DSA META-INF/*.SF -->
<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">
<!-- 设置jar包的入口类(可选) -->
<mainClass>com.office.flink.demo.WordCount</mainClass>
</transformer>
</transformers>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
+、JAVA
package com.office.flink.demo;
import org.apache.flink.api.common.functions.FlatMapFunction;
import org.apache.flink.api.common.functions.MapFunction;
import org.apache.flink.api.java.DataSet;
import org.apache.flink.api.java.ExecutionEnvironment;
import org.apache.flink.api.java.operators.AggregateOperator;
import org.apache.flink.api.java.operators.UnsortedGrouping;
import org.apache.flink.api.java.tuple.Tuple2;
import org.apache.flink.util.Collector;
/**
* 主函数
*
* @Author jolejian
* @Date: 2021/3/27 0027 14:03
*/
public class WordCount {
public static void main(String[] args) throws Exception {
//TODO 0.env
ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
//TODO 1.source
DataSet<String> lines = env.fromElements(
"itcast hadoop spark",
"itcast hadoop spark",
"itcast hadoop",
"itcast"
);
//TODO 2.transformation 切割
DataSet<String> words = lines.flatMap(new FlatMapFunction<String, String>() {
@Override
public void flatMap(String value, Collector<String> out) throws Exception {
//value表示每一行数据
String[] arr = value.split(" ");
for (String word : arr) {
out.collect(word);
}
}
});
//记为1
DataSet<Tuple2<String, Integer>> wordAndOne = words.map(new MapFunction<String, Tuple2<String, Integer>>() {
@Override
public Tuple2<String, Integer> map(String value) throws Exception {
//value就是每一个单词
return Tuple2.of(value, 1);
}
});
//分组
UnsortedGrouping<Tuple2<String, Integer>> grouped = wordAndOne.groupBy(0);
//聚合
AggregateOperator<Tuple2<String, Integer>> result = grouped.sum(1);
//TODO 3.sink
result.print();
//TODO 4.execute 启动并等待程序结束
// env.execute();
}
}