Spark(1)-wordCount入门

1. 创建Maven项目

"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>4.0.0modelVersion>
 
    <groupId>com.wakedatagroupId>
    <artifactId>codeartifactId>
    <version>1.0-SNAPSHOTversion>
 
 
    <properties>
        <maven.compiler.source>8maven.compiler.source>
        <maven.compiler.target>8maven.compiler.target>
        <encoding>UTF-8encoding>
        <spark.version>3.4.1spark.version>
        <scala.version>2.12.14scala.version>
    properties>
 
    <dependencies>
       
        <dependency>
            <groupId>org.scala-langgroupId>
            <artifactId>scala-libraryartifactId>
            <version>${scala.version}version>
        dependency>
 
        
        <dependency>
            <groupId>org.apache.sparkgroupId>
            <artifactId>spark-core_2.12artifactId>
            <version>${spark.version}version>
        dependency>
    dependencies>
 
    <build>
        
        <sourceDirectory>src/main/scalasourceDirectory>
        <testSourceDirectory>src/test/scalatestSourceDirectory>
        
        <plugins>
            <plugin>
                <groupId>net.alchim31.mavengroupId>
                <artifactId>scala-maven-pluginartifactId>
                <version>3.2.2version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compilegoal>
                            <goal>testCompilegoal>
                        goals>
                        <configuration>
                            <args>
                                
                                <arg>-dependencyfilearg>
                                <arg>${project.build.directory}/.scala_dependenciesarg>
                            args>
                        configuration>
                    execution>
                executions>
            plugin>
 
            
            <plugin>
                <groupId>org.apache.maven.pluginsgroupId>
                <artifactId>maven-shade-pluginartifactId>
                <version>2.4.3version>
                <executions>
                    <execution>
                        <phase>packagephase>
                        <goals>
                            <goal>shadegoal>
                        goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SFexclude>
                                        <exclude>META-INF/*.DSAexclude>
                                        <exclude>META-INF/*.RSAexclude>
                                    excludes>
                                filter>
                            filters>
                            <transformers>
                                <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
                                    <resource>reference.confresource>
                                transformer>
                                <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass>cn.itcast.rpc.MastermainClass> 
                                transformer>
                            transformers>
                        configuration>
                    execution>
                executions>
            plugin>
        plugins>
    build>
 
project>

2.目录结构

3. 代码实现

package sparkCore
 
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}
 
 
/***
 * 1. 创建SparkContext
 * 2. 创建RDD
 * 3. 调用RDD的Transformation算子
 * 4. 调用Action
 * 5. 释放资源
 */
 
object wordcount_01 {
 
  def main(args: Array[String]): Unit = {
 
    val conf:SparkConf = new SparkConf().setAppName("WordCount").setMaster("local")
    //创建SparkContext，使⽤SparkContext来创建RDD
    val sc: SparkContext = new SparkContext(conf)
 
    //spark写Spark程序，就是对抽象的神奇的⼤集合【RDD】编程，调⽤它⾼度封装的API //使⽤SparkContext创建RDD
    val lines: RDD[String] = sc.textFile("./data/words.txt")
 
    //切分压平
    val words: RDD[String] = lines.flatMap(_.split(" "))
 
    将单词和⼀组合放在元组中
    val wordsAndOne: RDD[(String, Int)] = words.map((_, 1))
 
    //分组聚合，reduceByKey可以先局部聚合再全局聚合
    val reduced: RDD[(String, Int)] = wordsAndOne.reduceByKey(_ + _)
 
    //排序
    val sorted: RDD[(String, Int)] = reduced.sortBy(_._2, false)
 
    //打印结果
    sorted.foreach(line => print(line))
 
    //释放资源
    sc.stop()
 
  }
 
}

运行结果：