Spark Batch Demo

原创转载请注明出处：https://www.cnblogs.com/agilestyle/p/14700811.html

Project Directory

Maven Dependency

<?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>org.fool</groupId>
    <artifactId>hellospark</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>8</maven.compiler.source>
        <maven.compiler.target>8</maven.compiler.target>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.12</artifactId>
            <version>3.1.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.12</artifactId>
            <version>3.1.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.12</artifactId>
            <version>3.1.1</version>
        </dependency>
    </dependencies>

    <build>
        <pluginManagement>
            <plugins>
                <plugin>
                    <groupId>org.apache.maven.plugins</groupId>
                    <artifactId>maven-compiler-plugin</artifactId>
                    <version>3.8.1</version>
                </plugin>
            </plugins>
        </pluginManagement>
    </build>
    
</project>

SpringBatchDemo.scala

package org.fool.spark

import org.apache.spark.sql.{SaveMode, SparkSession}

object SparkBatchDemo {
  def main(args: Array[String]): Unit = {
    val hdfsSourcePath = "hdfs://127.0.0.1:9000/input/people.json"

    val sparkSession = SparkSession.builder().appName("SparkBatchDemo").master("local").getOrCreate();

    val df = sparkSession.read.json(hdfsSourcePath)

    df.show()
    df.printSchema()

    df.select("name").show()
    df.groupBy("age").count().show()

    val hdfsOutputPath = "hdfs://127.0.0.1:9000/output/"

    df.write.mode(SaveMode.Overwrite).json(hdfsOutputPath)

    sparkSession.close()
  }
}

Note: 先从HDFS读，然后show，最后再写回HDFS

people.json

{"name":"Caocao","create_time":"2021-06-22 01:45:52.478","update_time":"2021-06-22 02:45:52.478"}
{"name":"Liubei", "age":30,"create_time":"2021-06-22 01:45:52.478","update_time":"2021-06-22 02:45:52.478"}
{"name":"Guanyu", "age":19,"create_time":"2021-06-22 01:45:52.478","update_time":"2021-06-22 02:45:52.478"}
{"name":"Zhangfei", "age":29,"create_time":"2021-06-22 01:45:52.478","update_time":"2021-06-22 02:45:52.478"}

执行前需要把people.json文件上传到HDFS上

cd $HADOOP_HOME/bin
./hdfs dfs -put ~/Desktop/people.json  /input

Run

HDFS Output

查看HDFS中output目录下的结果