├── .gitignore ├── README.md ├── pom.xml └── src ├── main ├── resources │ └── log4j.properties └── scala │ └── org │ └── anish │ └── spark │ └── etl │ ├── ProcessData.scala │ └── hive │ ├── Constants.scala │ ├── DemoRunner.scala │ ├── HiveSetup.scala │ └── LoadToHive.scala └── test ├── resources ├── expectedOutputs │ └── cleanedEmails │ │ └── correctEmailIds.csv ├── input_data │ └── testData.csv └── log4j.properties └── scala └── org └── anish └── spark ├── SparkTestUtils.scala └── etl └── ProcessDataTest.scala /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/README.md -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/pom.xml -------------------------------------------------------------------------------- /src/main/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/src/main/resources/log4j.properties -------------------------------------------------------------------------------- /src/main/scala/org/anish/spark/etl/ProcessData.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/src/main/scala/org/anish/spark/etl/ProcessData.scala -------------------------------------------------------------------------------- /src/main/scala/org/anish/spark/etl/hive/Constants.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/src/main/scala/org/anish/spark/etl/hive/Constants.scala -------------------------------------------------------------------------------- /src/main/scala/org/anish/spark/etl/hive/DemoRunner.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/src/main/scala/org/anish/spark/etl/hive/DemoRunner.scala -------------------------------------------------------------------------------- /src/main/scala/org/anish/spark/etl/hive/HiveSetup.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/src/main/scala/org/anish/spark/etl/hive/HiveSetup.scala -------------------------------------------------------------------------------- /src/main/scala/org/anish/spark/etl/hive/LoadToHive.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/src/main/scala/org/anish/spark/etl/hive/LoadToHive.scala -------------------------------------------------------------------------------- /src/test/resources/expectedOutputs/cleanedEmails/correctEmailIds.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/src/test/resources/expectedOutputs/cleanedEmails/correctEmailIds.csv -------------------------------------------------------------------------------- /src/test/resources/input_data/testData.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/src/test/resources/input_data/testData.csv -------------------------------------------------------------------------------- /src/test/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/src/test/resources/log4j.properties -------------------------------------------------------------------------------- /src/test/scala/org/anish/spark/SparkTestUtils.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/src/test/scala/org/anish/spark/SparkTestUtils.scala -------------------------------------------------------------------------------- /src/test/scala/org/anish/spark/etl/ProcessDataTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/anish749/spark2-etl-examples/HEAD/src/test/scala/org/anish/spark/etl/ProcessDataTest.scala --------------------------------------------------------------------------------