<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>
注:pom依赖在业务实施中是极其重要的一环,相当于配置文件,例如可能需要的 jar 包,可能需要的 Scala 语言版本都在此处进行配置 等等
创建数据库
CREATE TABLE `data` (
`id` int(11) NOT NULL AUTO_INCREMENT,
`name` varchar(255) DEFAULT NULL,
`age` int(11) DEFAULT NULL,
PRIMARY KEY (`id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;
业务逻辑
1、创建本地环境,并设置日志提示级别
val conf: SparkConf = new SparkConf().setAppName(“spark”).setMaster(“local[*]”)
val sc: SparkContext = new SparkContext(conf)
sc.setLogLevel(“WARN”)
2、加载数据,创建RDD
val dataRDD: RDD[(String, Int)] = sc.makeRDD(List((“tuomasi”, 21), (“孙悟空”, 19), (“猪八戒”, 20)))
3、分区迭代
dataRDD.foreachPartition(iter => {
})
4、加载驱动
val conn: Connection = DriverManager.getConnection(“jdbc:mysql://localhost:3306/bigdata?characterEncoding=UTF-8”, “root”, “123456”)
5、封装SQL语句
val sql: String = “INSERT INTO
data
(id
,name
,age
) VALUES (NULL, ?, ?);”
val ps: PreparedStatement = conn.prepareStatement(sql)
6、数据处理
iter.foreach(t => { //t就表示每一条数据
val name: String = t._1
val age: Int = t._2
ps.setString(1, name)
ps.setInt(2, age)
ps.addBatch()
})
ps.executeBatch()
7、关闭连接
if (conn != null) conn.close()
if (ps != null) ps.close()
8、读取数据库
val getConnection = () => DriverManager.getConnection(“jdbc:mysql://localhost:3306/bigdata?characterEncoding=UTF-8”, “root”, “123456”)
9、SQL语句上下界设定以及分区数设置
val studentTupleRDD: JdbcRDD[(Int, String, Int)] = new JdbcRDD[(Int, String, Int)](
sc,
getConnection,
sql,
1, //id为1~20之间的记录进行提取
20,
1,
mapRow
)