flink 离线 wc

pom文件

<?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.test</groupId>
    <artifactId>test-flink</artifactId>
    <version>1.0</version>

    <properties>
        <project.build.sourceEncoding>utf-8</project.build.sourceEncoding>
        <flink.version>1.10.0</flink.version>
        <scala.version>2.12.6</scala.version>
        <scala.binary.version>2.12</scala.binary.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-scala_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-streaming-scala_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.flink</groupId>
            <artifactId>flink-connector-kafka_${scala.binary.version}</artifactId>
            <version>${flink.version}</version>
        </dependency>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>1.7.7</version>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.17</version>
        </dependency>
        <dependency>
            <groupId>com.fasterxml.jackson.core</groupId>
            <artifactId>jackson-databind</artifactId>
            <version>2.10.2</version>
        </dependency>
        <!--<dependency>
            <groupId>net.sf.json-lib</groupId>
            <artifactId>json-lib</artifactId>
            <version>2.4</version>
        </dependency>-->
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>2.2.0</version>
        </dependency>
        <dependency>
            <groupId>org.elasticsearch</groupId>
            <artifactId>elasticsearch</artifactId>
            <version>7.3.1</version>
        </dependency>
        <dependency>
            <groupId>org.elasticsearch.client</groupId>
            <artifactId>elasticsearch-rest-high-level-client</artifactId>
            <version>7.3.1</version>
        </dependency>
        <dependency>
            <groupId>org.eclipse.jetty</groupId>
            <artifactId>jetty-util-ajax</artifactId>
            <version>9.4.26.v20200117</version>
        </dependency>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.39</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>

代码

import org.apache.flink.api.scala._
object FlinkDemo01_DataSet_wc {
    def main(args: Array[String]): Unit = {
        //1 创建执行环境
        val env = ExecutionEnvironment.getExecutionEnvironment
        //2 读取数据
        val ds: DataSet[String] = env.readTextFile("file:///I:\projectImplement\dataWareHouse\test-es\data\word.log")
        //3 执行
        val words: DataSet[String] = ds.flatMap(_.split(" "))
        val pairs = words.map((_,1))
        val keyAndNums: GroupedDataSet[(String, Int)] = pairs.groupBy(0)
        val result: AggregateDataSet[(String, Int)] = keyAndNums.sum(1)
        result.print()
    }
}