Commit 23a41958 23a41958491839ca6a4049a315475cea8c8ec641 by zhanghao

commit

1 parent db9ebff4
......@@ -12,9 +12,12 @@
<url>http://maven.apache.org</url>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<encoding>UTF-8</encoding>
<maven.compiler.source>1.8</maven.compiler.source>
<maven.compiler.target>1.8</maven.compiler.target>
<scala.tools.version>2.11</scala.tools.version>
<scala.version>2.11.8</scala.version>
<spark.version>2.4.3</spark.version>
<hadoop.version>2.6.0-cdh5.15.1</hadoop.version>
</properties>
......@@ -42,51 +45,90 @@
<artifactId>fastjson</artifactId>
<version>1.2.76</version>
</dependency>
<dependency>
<groupId>org.scala-lang</groupId>
<artifactId>scala-library</artifactId>
<version>${scala.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>${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>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.47</version>
</dependency>
<dependency>
<groupId>com.typesafe</groupId>
<artifactId>config</artifactId>
<version>1.3.3</version>
</dependency>
<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-jdbc</artifactId>
<version>1.2.1</version>
</dependency>
<dependency>
<groupId>org.apache.kudu</groupId>
<artifactId>kudu-client</artifactId>
<version>1.7.0</version>
</dependency>
<dependency>
<groupId>org.apache.kudu</groupId>
<artifactId>kudu-spark2_2.11</artifactId>
<version>1.7.0</version>
</dependency>
</dependencies>
<build>
<pluginManagement><!-- lock down plugins versions to avoid using Maven defaults (may be moved to parent pom) -->
<plugins>
<!-- clean lifecycle, see https://maven.apache.org/ref/current/maven-core/lifecycles.html#clean_Lifecycle -->
<plugin>
<artifactId>maven-clean-plugin</artifactId>
<version>3.1.0</version>
</plugin>
<!-- default lifecycle, jar packaging: see https://maven.apache.org/ref/current/maven-core/default-bindings.html#Plugin_bindings_for_jar_packaging -->
<plugin>
<artifactId>maven-resources-plugin</artifactId>
<version>3.0.2</version>
</plugin>
<plugin>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.8.0</version>
</plugin>
<plugin>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.22.1</version>
</plugin>
<plugin>
<artifactId>maven-jar-plugin</artifactId>
<version>3.0.2</version>
</plugin>
<plugin>
<artifactId>maven-install-plugin</artifactId>
<version>2.5.2</version>
</plugin>
<plugin>
<artifactId>maven-deploy-plugin</artifactId>
<version>2.8.2</version>
</plugin>
<!-- site lifecycle, see https://maven.apache.org/ref/current/maven-core/lifecycles.html#site_Lifecycle -->
<plugin>
<artifactId>maven-site-plugin</artifactId>
<version>3.7.1</version>
</plugin>
<plugin>
<artifactId>maven-project-info-reports-plugin</artifactId>
<version>3.0.0</version>
</plugin>
</plugins>
</pluginManagement>
<plugins>
<plugin>
<!-- see http://davidb.github.com/scala-maven-plugin -->
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.1.3</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>2.13</version>
<configuration>
<useFile>false</useFile>
<disableXmlReport>true</disableXmlReport>
<!-- If you have classpath issue like NoDefClassError,... -->
<!-- useManifestOnlyJar>false</useManifestOnlyJar -->
<includes>
<include>**/*Test.*</include>
<include>**/*Suite.*</include>
</includes>
</configuration>
</plugin>
</plugins>
</build>
</project>
......
......@@ -23,6 +23,7 @@ public class ETLApp {
FileSystem fileSystem = FileSystem.get(configuration);
Path outputPath = new Path(args[1]);
// Path outputPath = new Path("./input/etl");
if(fileSystem.exists(outputPath)) {
fileSystem.delete(outputPath,true);
}
......@@ -38,6 +39,8 @@ public class ETLApp {
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// FileInputFormat.setInputPaths(job, new Path("./input/data/log-2021-04-13.03.log"));
// FileOutputFormat.setOutputPath(job, new Path("./input/etl"));
job.waitForCompletion(true);
}
......
package com.bigdata.stest
import org.apache.spark.{SparkConf, SparkContext}
object SparkWordCountApp {
def main(args: Array[String]): Unit = {
val sparkConf = new SparkConf()
sparkConf.setMaster("local")
sparkConf.setAppName("SparkWordCountApp")
val sc = new SparkContext(sparkConf)
// val rdd = sc.textFile("./input/data/input.txt")
// rdd.collect().foreach(println)
sc.stop()
}
}