版本
scala : 2.11 spark : 2.20
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>org.exercise</groupId> <artifactId>scala</artifactId> <version>1.0-SNAPSHOT</version> <properties> <maven.compiler.source>1.8</maven.compiler.source> <maven.compiler.target>1.8</maven.compiler.target> <scala.version>2.11.8</scala.version> <spark.version>2.2.0</spark.version> <hadoop.version>2.7.3</hadoop.version> <encoding>UTF-8</encoding> <akka.version>2.4.17</akka.version> <scala.compat.version>2.11</scala.compat.version> <lucene.version>6.5.1</lucene.version> </properties> <dependencies> <dependency> <groupId>org.apache.httpcomponents</groupId> <artifactId>httpclient</artifactId> <version>4.5.2</version> </dependency> <dependency> <groupId>org.apache.logging.log4j</groupId> <artifactId>log4j-api</artifactId> <version>2.3</version> </dependency> <dependency> <groupId>commons-logging</groupId> <artifactId>commons-logging</artifactId> <version>1.2</version> </dependency> <!-- <dependency>--> <!-- <groupId>org.slf4j</groupId>--> <!-- <artifactId>slf4j-log4j12</artifactId>--> <!-- <version>1.7.25</version>--> <!-- <scope>test</scope>--> <!-- </dependency>--> <dependency> <groupId>org.slf4j</groupId> <artifactId>slf4j-nop</artifactId> <version>1.7.2</version> </dependency> <!-- lucene的核心 --> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-core</artifactId> <version>${lucene.version}</version> </dependency> <!-- lucene的分词器,有标准的英文相关的分词器,没有中文的 --> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-analyzers-common</artifactId> <version>${lucene.version}</version> </dependency> <!-- 查询解析器 --> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-queryparser</artifactId> <version>${lucene.version}</version> </dependency> <!-- 各种查询方式 --> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-queries</artifactId> <version>${lucene.version}</version> </dependency> <!-- 关键字高亮 --> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-highlighter</artifactId> <version>${lucene.version}</version> </dependency> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-demo</artifactId> <version>${lucene.version}</version> </dependency> <dependency> <groupId>junit</groupId> <artifactId>junit</artifactId> <version>4.12</version> </dependency> <dependency> <groupId>log4j</groupId> <artifactId>log4j</artifactId> <version>1.2.17</version> </dependency> <!-- <dependency>--> <!-- <groupId>org.slf4j</groupId>--> <!-- <artifactId>slf4j-api</artifactId>--> <!-- <version>1.7.22</version>--> <!-- </dependency>--> <!--######################################################--> <!-- es的客户端--> <dependency> <groupId>org.elasticsearch.client</groupId> <artifactId>transport</artifactId> <version>5.4.3</version> </dependency> <!-- 依赖2.x的log4j --> <dependency> <groupId>org.apache.logging.log4j</groupId> <artifactId>log4j-api</artifactId> <version>2.8.2</version> </dependency> <dependency> <groupId>org.apache.logging.log4j</groupId> <artifactId>log4j-core</artifactId> <version>2.8.2</version> </dependency> <!-- 单元测试 --> <dependency> <groupId>junit</groupId> <artifactId>junit</artifactId> <version>4.12</version> </dependency> <!--###########################################################--> <dependency> <groupId>com.github.scopt</groupId> <artifactId>scopt_2.10</artifactId> <version>3.2.0</version> </dependency> <!-- 添加akka的actor依赖 --> <dependency> <groupId>com.typesafe.akka</groupId> <artifactId>akka-actor_${scala.compat.version}</artifactId> <version>${akka.version}</version> </dependency> <!-- 多进程之间的Actor通信 --> <dependency> <groupId>com.typesafe.akka</groupId> <artifactId>akka-remote_${scala.compat.version}</artifactId> <version>${akka.version}</version> </dependency> <!-- 导入scala的依赖 --> <dependency> <groupId>org.scala-lang</groupId> <artifactId>scala-library</artifactId> <version>${scala.version}</version> </dependency> <!-- 导入spark的依赖 --> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-core_2.11</artifactId> <version>${spark.version}</version> </dependency> <!-- 指定hadoop-client API的版本 --> <dependency> <groupId>org.apache.hadoop</groupId> <artifactId>hadoop-client</artifactId> <version>${hadoop.version}</version> </dependency> <!-- 导入spark sql的依赖 --> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-sql_2.11</artifactId> <version>${spark.version}</version> </dependency> <!-- spark如果想整合Hive,必须加入hive的支持 --> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-hive_2.11</artifactId> <version>2.2.0</version> </dependency> <!-- spark steaming的依赖 --> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-streaming_2.11</artifactId> <version>2.2.0</version> </dependency> <!-- spark-mllib的依赖 --> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-mllib_2.11</artifactId> <version>2.2.0</version> </dependency> <!-- sparkSteaming跟Kafka整合的依赖 --> <dependency> <groupId>org.apache.spark</groupId> <artifactId>spark-streaming-kafka-0-8_2.11</artifactId> <version>${spark.version}</version> </dependency> <!-- mysql的连接驱动依赖 --> <dependency> <groupId>mysql</groupId> <artifactId>mysql-connector-java</artifactId> <version>8.0.16</version> </dependency> <dependency> <groupId>redis.clients</groupId> <artifactId>jedis</artifactId> <version>2.9.0</version> </dependency> </dependencies> <build> <pluginManagement> <plugins> <!-- 编译scala的插件 --> <plugin> <groupId>net.alchim31.maven</groupId> <artifactId>scala-maven-plugin</artifactId> <version>3.2.2</version> </plugin> <!-- 编译java的插件 --> <plugin> <groupId>org.apache.maven.plugins</groupId> <artifactId>maven-compiler-plugin</artifactId> <version>3.5.1</version> </plugin> </plugins> </pluginManagement> <plugins> <plugin> <groupId>net.alchim31.maven</groupId> <artifactId>scala-maven-plugin</artifactId> <executions> <execution> <id>scala-compile-first</id> <phase>process-resources</phase> <goals> <goal>add-source</goal> <goal>compile</goal> </goals> </execution> <execution> <id>scala-test-compile</id> <phase>process-test-resources</phase> <goals> <goal>testCompile</goal> </goals> </execution> </executions> </plugin> <plugin> <groupId>org.apache.maven.plugins</groupId> <artifactId>maven-compiler-plugin</artifactId> <executions> <execution> <phase>compile</phase> <goals> <goal>compile</goal> </goals> </execution> </executions> </plugin> <!-- 打jar插件 --> <plugin> <groupId>org.apache.maven.plugins</groupId> <artifactId>maven-shade-plugin</artifactId> <version>2.4.3</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> </configuration> </execution> </executions> </plugin> </plugins> </build> </project>View Code
2、FavTeacher.scala
import java.net.URL import org.apache.spark.rdd.RDD import org.apache.spark.{SparkConf, SparkContext} object FavTeacher { def main(args: Array[String]): Unit = { val conf = new SparkConf().setAppName("FavTeacher").setMaster("local[4]") val sc = new SparkContext(conf) //指定以后从哪里读取数据 val lines: RDD[String] = sc.textFile("F:\\Java\\scala\\src\\main\\resources\\spart_data\\topN\\input\\teacher.log") //整理数据 val teacherAndOne = lines.map(line => { val index = line.lastIndexOf("/") val teacher = line.substring(index + 1) //val httpHost = line.substring(0, index) //val subject = new URL(httpHost).getHost.split("[.]")(0) (teacher, 1) }) //聚合 val reduced: RDD[(String, Int)] = teacherAndOne.reduceByKey(_+_) //排序 val sorted: RDD[(String, Int)] = reduced.sortBy(_._2, false) //触发Action执行计算 val reslut: Array[(String, Int)] = sorted.collect() //打印 println(reslut.toBuffer) sc.stop() } }