IDEA编写Spark程序
1、 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>
<!-- 指定仓库位置，依次为aliyun、cloudera和jboss仓库 -->
<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>${spark.version}</version>
</dependency>
<!--<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.6.0-mr1-cdh5.14.0</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.2.0-cdh5.14.0</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>1.2.0-cdh5.14.0</version>
</dependency>-->
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.7.4</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.3.1</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>1.3.1</version>
</dependency>
<dependency>
<groupId>com.typesafe</groupId>
<artifactId>config</artifactId>
<version>1.3.3</version>
</dependency>
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.38</version>
</dependency>
</dependencies>
<build>
<sourceDirectory>src/main/scala</sourceDirectory>
<testSourceDirectory>src/test/scala</testSourceDirectory>
<plugins>
<!-- 指定编译java的插件 -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.5.1</version>
</plugin>
<!-- 指定编译scala的插件 -->
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.2.2</version>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
<configuration>
<args>
<arg>-dependencyfile</arg>
<arg>${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>
前提：创建一个maven项目
编写代码
1、创建spark conf
2、实例一个sparkcontext
3、读物数据，对数据进行操作（业务逻辑）
4、保存最终的结果
Jar包执行
讲代码到导出成为jar文件，上传到集群，通过spark-submit提交任务
本地运行
object WordCount {
def main(args: Array[String]): Unit = {
//1.创建SparkContext
val config = new SparkConf().setAppName("wc").setMaster("local[*]")
val sc = new SparkContext(config)
sc.setLogLevel("WARN")
//2.读取文件
val fileRDD: RDD[String] = sc.textFile("F:\\第四学期的大数据资料\\day01三月份资料\\第四周\\day04\\4.2号练习题\\word.txt")
//3.处理数据
val wordRDD: RDD[String] = fileRDD.flatMap(_.split(" "))
//3.2每个单词记为1
val wordAndOneRDD: RDD[(String, Int)] = wordRDD.map((_,1))
//3.3根据key进行聚合,统计每个单词的数量
val wordAndCount: RDD[(String, Int)] = wordAndOneRDD.reduceByKey(_+_)
//4.收集结果
val result: Array[(String, Int)] = wordAndCount.collect()
result.foreach(println)
}
}
集群运行
object WordCountJ {
def main(args: Array[String]): Unit = {
//1.创建SparkContext
val config = new SparkConf().setAppName("wc")//.setMaster("local[*]")
val sc = new SparkContext(config)
sc.setLogLevel("WARN")
//2.读取文件
val fileRDD: RDD[String] = sc.textFile(args(0)) //文件输入路径
//3.处理数据
val wordRDD: RDD[String] = fileRDD.flatMap(_.split(" "))
//3.2每个单词记为1
val wordAndOneRDD: RDD[(String, Int)] = wordRDD.map((_,1))
//3.3根据key进行聚合,统计每个单词的数量
val wordAndCount: RDD[(String, Int)] = wordAndOneRDD.reduceByKey(_+_)
wordAndCount.saveAsTextFile(args(1))//文件输出路径
}
}
●打包
上传
执行命令提交到YARN集群
/export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/bin/spark-submit
–class demo02.WordCountJ
–master yarn
–deploy-mode cluster
–driver-memory 1g
–executor-memory 1g
–executor-cores 2
–queue default
/export/pot/Demo06_Spark_01-1.0-SNAPSHOT.jar
hdfs://hadoop01:8020/words.txt
hdfs://hadoop01:8020/wordcount/output5
执行命令提交到Spark-HA集群
/export/servers/spark-2.2.0-bin-2.6.0-cdh5.14.0/bin/spark-submit
–class cn.itcast.sparkhello.WordCount
–master spark://hadoop01:7077,hadoop02:7077
–executor-memory 1g
–total-executor-cores 2
/export/pot/Demo06_Spark_01-1.0-SNAPSHOT.jar
hdfs://hadoop01:8020/words.txt
hdfs://hadoop01:8020/wordcount/output4
