<?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.atguigu.flink</groupId> <artifactId>FlinkTutorial</artifactId> <version>1.0-SNAPSHOT</version> <dependencies> <dependency> <groupId>org.apache.flink</groupId> <artifactId>flink-scala_2.11</artifactId> <version>1.7.2</version> </dependency> <!-- https://mvnrepository.com/artifact/org.apache.flink/flink-streaming-scala --> <dependency> <groupId>org.apache.flink</groupId> <artifactId>flink-streaming-scala_2.11</artifactId> <version>1.7.2</version> </dependency> </dependencies> <build> <plugins> <!-- 该插件用于将 Scala 代码编译成 class 文件 --> <plugin> <groupId>net.alchim31.maven</groupId> <artifactId>scala-maven-plugin</artifactId> <version>3.4.6</version> <executions> <execution> <!-- 声明绑定到 maven 的 compile 阶段 --> <goals> <goal>testCompile</goal> </goals> </execution> </executions> </plugin> <plugin> <groupId>org.apache.maven.plugins</groupId> <artifactId>maven-assembly-plugin</artifactId> <version>3.0.0</version> <configuration> <descriptorRefs> <descriptorRef>jar-with-dependencies</descriptorRef> </descriptorRefs> </configuration> <executions> <execution> <id>make-assembly</id> <phase>package</phase> <goals> <goal>single</goal> </goals> </execution> </executions> </plugin> </plugins> </build> </project>
object WordCount { def main(args: Array[String]): Unit = { // 创建执行环境 val env = ExecutionEnvironment.getExecutionEnvironment // 从文件中读取数据 val inputPath = "D:\\Projects\\BigData\\TestWC1\\src\\main\\resources\\hello.txt" val inputDS: DataSet[String] = env.readTextFile(inputPath) // 分词之后，对单词进行 groupby 分组，然后用 sum 进行聚合 val wordCountDS: AggregateDataSet[(String, Int)] = inputDS.flatMap(_.split(" ")).map((_, 1)).groupBy(0).sum(1) // 打印输出 wordCountDS.print() } }
object StreamWordCount { def main(args: Array[String]): Unit = { // 从外部命令中获取参数 val params: ParameterTool = ParameterTool.fromArgs(args) val host: String = params.get("host") val port: Int = params.getInt("port") // 创建流处理环境 val env = StreamExecutionEnvironment.getExecutionEnvironment // 接收 socket 文本流 val textDstream: DataStream[String] = env.socketTextStream(host, port) // flatMap 和 Map 需要引用的隐式转换 import org.apache.flink.api.scala._ val dataStream: DataStream[(String, Int)] = textDstream.flatMap(_.split("\\s")).filter(_.nonEmpty).map((_, 1)).keyBy(0).sum(1) dataStream.print().setParallelism(1) // 启动 executor，执行任务 env.execute("Socket stream word count") } }
nc -lk 7777
原文：https://www.cnblogs.com/qiu-hua/p/13412841.html
