Scala +Spark+Hadoop+Zookeeper+IDEA实现WordCount单词计数（简单实例-上）

<?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.mcb.scala02</groupId>
    <artifactId>scala02</artifactId>
    <version>1.0-SNAPSHOT</version>
 
    <properties>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <encoding>UTF-8</encoding>
        <scala.version>2.10.5</scala.version>
        <spark.version>1.6.3</spark.version>
        <hadoop.version>2.7.5</hadoop.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
    </dependencies>
    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.0</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <arg>-make:transitive</arg>
                                <arg>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-surefire-plugin</artifactId>
                <version>2.18.1</version>
                <configuration>
                    <useFile>false</useFile>
                    <disableXmlReport>true</disableXmlReport>
                    <includes>
                        <include>**/*Test.*</include>
                        <include>**/*Suite.*</include>
                    </includes>
                </configuration>
            </plugin>
 
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                            <transformers>
                                <transformer
                                        implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass>day05.SparkWordCount</mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

package day05
 
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}
 
import scala.collection.mutable
 
object SparkWordCount {
 
  def main(args: Array[String]): Unit = {
    //配置信息类
    //1，setAppName(任务名称) setMaster(表示开启多少个线程运行)
    val conf: SparkConf = new SparkConf().setAppName("SparkWordCount").setMaster("local[*]")
 
    //上下文对象
    val sc: SparkContext = new SparkContext(conf)
 
    //读取数据(数据通过数组 args进入)
    val lines: RDD[String] = sc.textFile(args(0))
 
    //处理数据
    val map01: RDD[(String, Int)] = lines.flatMap(_.split(" ")).map((_,1))
    val wordCount: RDD[(String, Int)] = map01.reduceByKey(_+_).sortBy(_._2,false)
 
    val wcToBuffer: mutable.Buffer[(String, Int)] = wordCount.collect().toBuffer
    println(wcToBuffer)
 
    sc.stop()
  }
}