Github user ravipesala commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/2614#discussion_r214529711
--- Diff:
examples/spark2/src/main/scala/org/apache/carbondata/examples/MVDataMapExample.scala
---
@@ -0,0 +1,125 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.carbondata.examples
+
+import java.io.File
+
+import org.apache.spark.sql.SparkSession
+
+import org.apache.carbondata.examples.util.ExampleUtils
+
+/**
+ * This example is for pre-aggregate tables.
+ */
+
+object MVDataMapExample {
+
+ def main(args: Array[String]) {
+ val spark = ExampleUtils.createCarbonSession("MVDataMapExample")
+ exampleBody(spark)
+ spark.close()
+ }
+
+ def exampleBody(spark: SparkSession): Unit = {
+ val rootPath = new File(this.getClass.getResource("/").getPath
+ + "../../../..").getCanonicalPath
+ val testData =
s"$rootPath/integration/spark-common-test/src/test/resources/sample.csv"
+
+ // 1. simple usage for Pre-aggregate tables creation and query
+ spark.sql("DROP TABLE IF EXISTS mainTable")
+ spark.sql("DROP TABLE IF EXISTS dimtable")
+ spark.sql(
+ """
+ | CREATE TABLE mainTable
+ | (id Int,
+ | name String,
+ | city String,
+ | age Int)
+ | STORED BY 'org.apache.carbondata.format'
+ """.stripMargin)
+
+ spark.sql(
+ """
+ | CREATE TABLE dimtable
+ | (name String,
+ | address String)
+ | STORED BY 'org.apache.carbondata.format'
+ """.stripMargin)
+
+ spark.sql(s"""LOAD DATA LOCAL INPATH '$testData' into table
mainTable""")
+
+ spark.sql(s"""insert into dimtable select name, concat(city, '
street1') as address from
+ |mainTable group by name, address""".stripMargin)
--- End diff --
It is for removing duplicates while insert into dimension table
---
