使用IDEA編寫Spark程序（4）

1、pom.xml

●創建Maven項目並補全目錄、配置pom.xml

		<?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>cn.itcast</groupId>
    <artifactId>SparkDemo</artifactId>
    <version>1.0-SNAPSHOT</version>
 
    <!-- 指定倉庫位置，依次爲aliyun、cloudera和jboss倉庫 -->
    <repositories>
        <repository>
            <id>aliyun</id>
            <url>http://maven.aliyun.com/nexus/content/groups/public/</url>
        </repository>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
        <repository>
            <id>jboss</id>
            <url>http://repository.jboss.com/nexus/content/groups/public</url>
        </repository>
    </repositories>
    <properties>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <encoding>UTF-8</encoding>
        <scala.version>2.11.8</scala.version>
        <scala.compat.version>2.11</scala.compat.version>
        <hadoop.version>2.7.4</hadoop.version>
        <spark.version>2.2.0</spark.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-hive_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-hive-thriftserver_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <!-- <dependency>
             <groupId>org.apache.spark</groupId>
             <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
             <version>${spark.version}</version>
         </dependency>-->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql-kafka-0-10_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
 
        <!--<dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0-mr1-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>1.2.0-cdh5.14.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>1.2.0-cdh5.14.0</version>
        </dependency>-->
 
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.7.4</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>1.3.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>1.3.1</version>
        </dependency>
        <dependency>
            <groupId>com.typesafe</groupId>
            <artifactId>config</artifactId>
            <version>1.3.3</version>
        </dependency>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.38</version>
        </dependency>
    </dependencies>
 
    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>
            <!-- 指定編譯java的插件 -->
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.5.1</version>
            </plugin>
            <!-- 指定編譯scala的插件 -->
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <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></mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

●maven-assembly-plugin和maven-shade-plugin的區別

https://blog.csdn.net/lisheng19870305/article/details/88300951

2、本地運行

package cn.itcast.sparkhello

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}


object WordCount {
  def main(args: Array[String]): Unit = {
    //1.創建SparkContext
    val config = new SparkConf().setAppName("wc").setMaster("local[*]")
    val sc = new SparkContext(config)
sc.setLogLevel("WARN")
    //2.讀取文件
    //A Resilient Distributed Dataset (RDD)彈性分佈式數據集
    //可以簡單理解爲分佈式的集合,但是spark對它做了很多的封裝,
    //讓程序員使用起來就像操作本地集合一樣簡單,這樣大家就很happy了
    val fileRDD: RDD[String] = sc.textFile("D:\\授課\\190429\\資料\\data\\words.txt")
    //3.處理數據
    //3.1對每一行按空切分並壓平形成一個新的集合中裝的一個個的單詞
    //flatMap是對集合中的每一個元素進行操作,再進行壓平
    val wordRDD: RDD[String] = fileRDD.flatMap(_.split(" "))
    //3.2每個單詞記爲1
    val wordAndOneRDD: RDD[(String, Int)] = wordRDD.map((_,1))
    //3.3根據key進行聚合,統計每個單詞的數量
    //wordAndOneRDD.reduceByKey((a,b)=>a+b)
    //第一個_:之前累加的結果
    //第二個_:當前進來的數據
    val wordAndCount: RDD[(String, Int)] = wordAndOneRDD.reduceByKey(_+_)
    //4.收集結果
    val result: Array[(String, Int)] = wordAndCount.collect()
    result.foreach(println)
  }
}

3、集羣運行

●修改代碼



package cn.itcast.sparkhello

import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}


object WordCount {
  def main(args: Array[String]): Unit = {
    //1.創建SparkContext
    val config = new SparkConf().setAppName("wc")//.setMaster("local[*]") 
    val sc = new SparkContext(config)
    sc.setLogLevel("WARN")
    //2.讀取文件
    //A Resilient Distributed Dataset (RDD)彈性分佈式數據集
    //可以簡單理解爲分佈式的集合,但是spark對它做了很多的封裝,
    //讓程序員使用起來就像操作本地集合一樣簡單,這樣大家就很happy了
    val fileRDD: RDD[String] = sc.textFile(args(0)) //文件輸入路徑
    //3.處理數據
    //3.1對每一行按空切分並壓平形成一個新的集合中裝的一個個的單詞
    //flatMap是對集合中的每一個元素進行操作,再進行壓平
    val wordRDD: RDD[String] = fileRDD.flatMap(_.split(" "))
    //3.2每個單詞記爲1
    val wordAndOneRDD: RDD[(String, Int)] = wordRDD.map((_,1))
    //3.3根據key進行聚合,統計每個單詞的數量
    //wordAndOneRDD.reduceByKey((a,b)=>a+b)
    //第一個_:之前累加的結果
    //第二個_:當前進來的數據
    val wordAndCount: RDD[(String, Int)] = wordAndOneRDD.reduceByKey(_+_)
    wordAndCount.saveAsTextFile(args(1))//文件輸出路徑
   //4.收集結果
   //val result: Array[(String, Int)] = wordAndCount.collect()
   //result.foreach(println)
  }
}

4、打包上傳

●執行命令提交到Spark-HA集羣

/export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/bin/spark-submit \
--class cn.itcast.sparkhello.WordCount \
--master spark://node01:7077,node02:7077 \
--executor-memory 1g \
--total-executor-cores 2 \
/root/wc.jar \
hdfs://node01:8020/aa.txt \
hdfs://node01:8020/cc

●執行命令提交到YARN集羣

/export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/bin/spark-submit \
--class cn.itcast.sparkhello.WordCount \
--master yarn \
--deploy-mode cluster \
--driver-memory 1g \
--executor-memory 1g \
--executor-cores 2 \
--queue default \
/root/wc.jar \
hdfs://node01:8020/wordcount/input/words.txt \
hdfs://node01:8020/wordcount/output5

Java8版[瞭解]

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import scala.Tuple2;

import java.util.Arrays;

public class WordCount_Java {
    public static void main(String[] args){
        SparkConf conf = new SparkConf().setAppName("wc").setMaster("local[*]");
        JavaSparkContext jsc = new JavaSparkContext(conf);
        JavaRDD<String> fileRDD = jsc.textFile("D:\\授課\\190429\\資料\\data\\words.txt");
        JavaRDD<String> wordRDD = fileRDD.flatMap(s -> Arrays.asList(s.split(" ")).iterator());
        JavaPairRDD<String, Integer> wordAndOne = wordRDD.mapToPair(w -> new Tuple2<>(w, 1));
        JavaPairRDD<String, Integer> wordAndCount = wordAndOne.reduceByKey((a, b) -> a + b);
        //wordAndCount.collect().forEach(t->System.out.println(t));
        wordAndCount.collect().forEach(System.out::println);
        //函數式編程的核心思想:行爲參數化!
    }
}

鐵鐵們，下期給大家分享SparkCore！