1. Scala代码
/**
*抽取Taredata数据库数据到HDFS
*/
object Td2Hdfs {
def main(args: Array[String]): Unit = {
val startTime = System.currentTimeMillis()
val spark = SparkSession
.builder()
//.master("local[2]")
.appName("Td2Hdfs")
.getOrCreate()
val jdbcDF = spark.read.format("jdbc")
.option("url", "jdbc:地址")
.option("dbtable", "数据库名字")
.option("user", "用户名")
.option("password", "密码")
.option("driver", "com.ncr.teradata.TeraDriver")
.load()
jdbcDF.printSchema()
jdbcDF.show(2)
jdbcDF.createOrReplaceTempView("spark")
spark.sql("select *,cast(from_unixtime(unix_timestamp()-86400,'yyyyMMdd') as STRING) as dtm from spark")
.write
.mode("overwrite")
.partitionBy("dtm")
.saveAsTable("hive表名")
val endTime = System.currentTimeMillis()
println("sucessful running time " + (endTime - startTime) + " ms")
spark.stop()
}
}
2.pom.xml 会多,不用的可以自己删掉
<?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.com.woof</groupId>
<artifactId>PgToHive</artifactId>
<version>7.0-SNAPSHOT</version>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
</properties>
<dependencyManagement>
<dependencies>
<!-- Camel BOM Apache一个开源规则引擎-->
<dependency>
<groupId>org.apache.camel</groupId>
<artifactId>camel-parent</artifactId>
<version>2.24.0</version>
<scope>import</scope>
<type>pom</type>
</dependency>
</dependencies>
</dependencyManagement>
<dependencies>
<!-- https://mvnrepository.com/artifact/org.apache.spark/spark-core -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>2.2.0</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.spark/spark-streaming-kafka -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka_2.11</artifactId>
<version>1.6.2</version>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.spark/spark-hive -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-hive_2.11</artifactId>
<version>2.2.0</version>
<scope>provided</scope>
</dependency>
<!-- https://mvnrepository.com/artifact/org.apache.spark/spark-streaming -->
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>2.2.0</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>2.2.0</version>
</dependency>
<dependency>
<groupId>org.apache.camel</groupId>
<artifactId>camel-core</artifactId>
</dependency>
<dependency>
<groupId>org.apache.camel</groupId>
<artifactId>camel-scala</artifactId>
</dependency>
<!-- scala -->
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>2.11.7</version>
</dependency>
<dependency>
<groupId>org.scala-lang.modules</groupId>
<artifactId>scala-xml_2.11</artifactId>
<version>1.0.6</version>
</dependency>
<!-- logging -->
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-api</artifactId>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-slf4j-impl</artifactId>
<scope>runtime</scope>
</dependency>
</dependencies>
<build>
<defaultGoal>install</defaultGoal>
<sourceDirectory>src/main/scala</sourceDirectory>
<plugins>
<!-- the Maven compiler plugin will compile Java source files -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.8.0</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-resources-plugin</artifactId>
<version>3.0.2</version>
<configuration>
<encoding>UTF-8</encoding>
</configuration>
</plugin>
<!-- the Maven Scala plugin will compile Scala source files -->
<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>
</execution>
</executions>
</plugin>
<!-- configure the eclipse plugin to generate eclipse project descriptors for a Scala project -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-eclipse-plugin</artifactId>
<version>2.10</version>
<configuration>
<projectnatures>
<projectnature>org.scala-ide.sdt.core.scalanature</projectnature>
<projectnature>org.eclipse.jdt.core.javanature</projectnature>
</projectnatures>
<buildcommands>
<buildcommand>org.scala-ide.sdt.core.scalabuilder</buildcommand>
</buildcommands>
<classpathContainers>
<classpathContainer>org.scala-ide.sdt.launching.SCALA_CONTAINER</classpathContainer>
<classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
</classpathContainers>
<excludes>
<exclude>org.scala-lang:scala-library</exclude>
<exclude>org.scala-lang:scala-compiler</exclude>
</excludes>
<sourceIncludes>
<sourceInclude>**/*.scala</sourceInclude>
<sourceInclude>**/*.java</sourceInclude>
</sourceIncludes>
</configuration>
</plugin>
<!-- allows the route to be run via 'mvn exec:java' -->
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>exec-maven-plugin</artifactId>
<version>1.6.0</version>
<configuration>
<mainClass>cn.com.woof.MyRouteMain</mainClass>
</configuration>
</plugin>
</plugins>
</build>
</project>
3. 提交命令
spark2-submit \
--class Td2Hdfs \
--driver-memory 4g \
--executor-memory 8g \
--master yarn \
4.如果出现乱码,请在代码里添加
.option("url","jdbc:teradata//organization.td.intranet,CHARSET=UTF8,TMODE=ANSI,user=G01159039")