maven_spark

1.创建项目

2.下载apache-maven-3.3.9-bin.tar.gz

3.修改配置文件

<localRepository>D:/module/maven/maven_repository</localRepository>

<mirrors>
<mirror>
<id>aliyunmaven</id>
<mirrorOf>central</mirrorOf>
<name>aliyun maven</name>
<url>https://maven.aliyun.com/repository/public </url>
</mirror>
</mirrors>

4.设置idea中的maven环境

 

 5.pom配置文件

<?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>spark_yarn</groupId>
    <artifactId>yarn</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <scala.version>2.11</scala.version>
        <scala.compat.version>2.11</scala.compat.version>
        <spark.version>2.2.0</spark.version>
        <hadoop.version>2.7.2</hadoop.version>
        <hbase.version>1.0</hbase.version>
    </properties>
    <!--<properties>-->
    <!--<scala.version>2.11</scala.version>-->
    <!--<scala.compat.version>2.11</scala.compat.version>-->
    <!--<spark.version>1.6.1</spark.version>-->
    <!--<hadoop.version>2.7.2</hadoop.version>-->
    <!--</properties>-->
    <repositories>
        <repository>
            <id>nexus-aliyun</id>
            <name>Nexus aliyun</name>
            <url>http://maven.aliyun.com/nexus/content/groups/public</url>
        </repository>
    </repositories>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>2.11.8</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>




        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-launcher_${scala.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>



        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>


        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-auth</artifactId>
            <version>${hadoop.version}</version>
        </dependency>





    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.scala-tools</groupId>
                <artifactId>maven-scala-plugin</artifactId>
                <version>2.15.2</version>
                <executions>
                    <execution>
                        <id>scala-compile-first</id>
                        <goals>
                            <goal>compile</goal>
                        </goals>
                        <configuration>
                            <includes>
                                <include>**/*.scala</include>
                            </includes>
                        </configuration>
                    </execution>
                    <execution>
                        <id>scala-test-compile</id>
                        <goals>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                </configuration>
            </plugin>
        </plugins>
    </build>






</project>

6.wordcout.scala

package atguigu
import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.SparkSession
object WC {
  def main(args: Array[String]): Unit = {

    //集群模式
    //    val sparkSession: SparkSession = SparkSession.builder().appName("My Scala Word Count").getOrCreate()

    //本地模式
    val sparkSession: SparkSession = SparkSession.builder().appName("My Scala Word Count").master("local").getOrCreate()

    val spark: SparkContext = sparkSession.sparkContext

    //    val result = spark.textFile(args(0))
    //      .flatMap(_.split(" "))
    //      .map((_, 1))
    //      .reduceByKey(_ + _).saveAsTextFile(args(1))


    //        val result = spark.textFile("input/hello.txt")
    //          .flatMap(_.split(" "))
    //          .map((_, 1))
    //          .reduceByKey(_ + _).saveAsTextFile("out")


    val dataRDD: RDD[String] = spark.textFile("input/hello.txt")
    println("dataRDD:")
    dataRDD.collect().foreach(println)

    val flatMapRDD: RDD[String] = dataRDD.flatMap(_.split(" "))
    println("flatMapRDD:")
    flatMapRDD.collect().foreach(println)

    val mapRDD: RDD[(String, Int)] = flatMapRDD .map((_, 1))
    println("mapRDD:")
    mapRDD.collect().foreach(println)

    val reduceByKeyRDD: RDD[(String, Int)] = mapRDD.reduceByKey(_ + _)
    println("reduceByKeyRDD:")
    reduceByKeyRDD.collect().foreach(println)

    reduceByKeyRDD.saveAsTextFile("out")





    spark.stop()

  }
}