一、本地运行spark程序
1、pom依赖
注：依赖配置项及其版本一定要与集群环境相适配
<?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> <repositories> <repository> <id>aliyun</id> <url>http://maven.aliyun.com/nexus/content/groups/public/</url> </repository> <repository> <id>apache</id> <url>https://repository.apache.org/content/repositories/snapshots/</url> </repository> <repository> <id>cloudera</id> <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url> </repository> </repositories> <properties> <encoding>UTF-8</encoding> <maven.compiler.source>1.8</maven.compiler.source> <maven.compiler.target>1.8</maven.compiler.target> <scala.version>2.12.11</scala.version> <spark.version>3.0.1</spark.version> <hadoop.version>2.7.5</hadoop.version> </properties> <dependencies> <!--依赖Scala语言--> <dependency> <groupId>org.scala-lang</groupId> <artifactId>scala-library</artifactId> <version>${scala.version}</version> </dependency> <!--SparkCore依赖--> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-core_2.12</artifactId> <version>${spark.version}</version> </dependency> <!-- spark-streaming--> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-streaming_2.12</artifactId> <version>${spark.version}</version> </dependency> <!--spark-streaming+Kafka依赖--> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-streaming-kafka-0-10_2.12</artifactId> <version>${spark.version}</version> </dependency> <!--SparkSQL依赖--> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-sql_2.12</artifactId> <version>${spark.version}</version> </dependency> <!--SparkSQL+ Hive依赖--> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-hive_2.12</artifactId> <version>${spark.version}</version> </dependency> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-hive-thriftserver_2.12</artifactId> <version>${spark.version}</version> </dependency> <!--StructuredStreaming+Kafka依赖--> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-sql-kafka-0-10_2.12</artifactId> <version>${spark.version}</version> </dependency> <!-- SparkMlLib机器学习模块,里面有ALS推荐算法--> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-mllib_2.12</artifactId> <version>${spark.version}</version> </dependency> <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-client</artifactId> <version>2.7.5</version> </dependency> <dependency> <groupId>com.hankcs</groupId> <artifactId>hanlp</artifactId> <version>portable-1.7.7</version> </dependency> <dependency> <groupId>mysql</groupId> <artifactId>mysql-connector-java</artifactId> <version>8.0.23</version> </dependency> <dependency> <groupId>redis.clients</groupId> <artifactId>jedis</artifactId> <version>2.9.0</version> </dependency> <dependency> <groupId>com.alibaba</groupId> <artifactId>fastjson</artifactId> <version>1.2.47</version> </dependency> <dependency> <groupId>org.projectlombok</groupId> <artifactId>lombok</artifactId> <version>1.18.2</version> <scope>provided</scope> </dependency> </dependencies> <build> <sourceDirectory>src/main/scala</sourceDirectory> <plugins> <!-- 指定编译java的插件 --> <plugin> <groupId>org.apache.maven.plugins</groupId> <artifactId>maven-compiler-plugin</artifactId> <version>3.5.1</version> </plugin> <!-- 指定编译scala的插件 --> <plugin> <groupId>net.alchim31.maven</groupId> <artifactId>scala-maven-plugin</artifactId> <version>3.2.2</version> <executions> <execution> <goals> <goal>compile</goal> <goal>testCompile</goal> </goals> <configuration> <args> <arg>-dependencyfile</arg> <arg>${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>
2、数据展示
3、代码编写
package org.example.spark import org.apache.spark.rdd.RDD import org.apache.spark.{SparkConf, SparkContext} object word { def main(args: Array[String]): Unit = { //准备环境 val conf = new SparkConf().setMaster("local[*]").setAppName("wordcount") val sc = new SparkContext(conf) //加载文件 val rdd1: RDD[String] = sc.textFile("data/input/words.txt") // 处理数据 val rdd2: RDD[String] = rdd1.flatMap(lp => { lp.split(" ") }) val rdd3: RDD[(String, Int)] = rdd2.map(it => (it, 1)) val rdd4: RDD[(String, Int)] = rdd3.reduceByKey((curr, agg) => curr + agg) val result: Array[(String, Int)] = rdd4.collect() result.foreach(i => println(i)) } }
4、本地运行
注：单词统计案例本地效果如图所示
二、集群运行spark程序
1、修改代码
val rdd1: RDD[String] = sc.textFile("hdfs:///input/wordcount.txt")
rdd4.saveAsTextFile("hdfs://192.168.231.247:8020/output/output1")
注：集群运行文件加载路径设置为hdfs，即每次集群运行从hdfs拿取数据，并将实时数据上传至hdfs
2、打包jar
注：双击maven中的package，maven会自动进行清除缓存，测试并打包为jar
3、找到项目路径中的jar包
注：jar包大小最小的为不是带全部依赖的jar包，在集群运行不需要全部的依赖，即上传最小依赖的jar包即可
4、上传至linux
注：此处使用xftp进行传输 jar包
5、启动 hadoop 以及 spark 集群
6、进入spark安装目录下执行
bin/spark-submit --class org.example.spark.word --master spark://master:8020 /input/original-SparkDemo-1.0-SNAPSHOT.jar
注：单词统计集群运行如图所示
7、进入hdfs web端目录进行查看
Spark-两种运行方式（本地运行，提交集群运行）完成
