Github user kunal642 commented on a diff in the pull request: https://github.com/apache/carbondata/pull/2951#discussion_r236646951 --- Diff: integration/spark-common-cluster-test/src/test/scala/org/apache/carbondata/cluster/sdv/generated/dli/CreateTableUsingSparkCarbonFileFormatTestCase.scala --- @@ -0,0 +1,484 @@ +/* + * 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.cluster.sdv.generated.dli + +import java.io.File +import java.text.SimpleDateFormat +import java.util.{Date, Random} + +import scala.collection.JavaConverters._ + +import org.apache.commons.io.FileUtils +import org.apache.commons.lang.RandomStringUtils +import org.scalatest.BeforeAndAfterAll +import org.apache.spark.util.SparkUtil + +import org.apache.carbondata.core.datastore.filesystem.CarbonFile +import org.apache.carbondata.core.datastore.impl.FileFactory +import org.apache.carbondata.core.metadata.datatype.DataTypes +import org.apache.carbondata.core.util.{CarbonProperties, CarbonUtil, DataFileFooterConverter} +import org.apache.carbondata.sdk.file.{CarbonWriter, Field, Schema} +import org.apache.spark.sql.Row +import org.apache.spark.sql.common.util.QueryTest + +import org.apache.carbondata.core.constants.CarbonCommonConstants +import org.apache.carbondata.core.datamap.DataMapStoreManager +import org.apache.carbondata.core.metadata.AbsoluteTableIdentifier +import org.apache.carbondata.core.metadata.blocklet.DataFileFooter + +class CreateTableUsingSparkCarbonFileFormatTestCase extends QueryTest with BeforeAndAfterAll { + + + + override def beforeAll(): Unit = { + sql("DROP TABLE IF EXISTS sdkOutputTable") + } + + override def afterAll(): Unit = { + CarbonProperties.getInstance() + .addProperty(CarbonCommonConstants.CARBON_MINMAX_ALLOWED_BYTE_COUNT, + CarbonCommonConstants.CARBON_MINMAX_ALLOWED_BYTE_COUNT_DEFAULT) + sql("DROP TABLE IF EXISTS sdkOutputTable") + } + + var writerPath = new File(this.getClass.getResource("/").getPath + + + "../." + + "./src/test/resources/SparkCarbonFileFormat/WriterOutput/") + .getCanonicalPath + //getCanonicalPath gives path with \, but the code expects /. + writerPath = writerPath.replace("\\", "/"); + + def buildTestData(): Any = { + + FileUtils.deleteDirectory(new File(writerPath)) + + val schema = new StringBuilder() + .append("[ \n") + .append(" {\"name\":\"string\"},\n") + .append(" {\"age\":\"int\"},\n") + .append(" {\"height\":\"double\"}\n") + .append("]") + .toString() + + try { + val builder = CarbonWriter.builder() + val writer = + builder.outputPath(writerPath).withCsvInput(Schema.parseJson(schema)).writtenBy("CreateTableUsingSparkCarbonFileFormatTestCase").build() + var i = 0 + while (i < 100) { + writer.write(Array[String]("robot" + i, String.valueOf(i), String.valueOf(i.toDouble / 2))) + i += 1 + } + writer.close() + } catch { + case _: Throwable => None + } + } + + def cleanTestData() = { + FileUtils.deleteDirectory(new File(writerPath)) + } + + def deleteIndexFile(path: String, extension: String) : Unit = { + val file: CarbonFile = FileFactory + .getCarbonFile(path, FileFactory.getFileType(path)) + + for (eachDir <- file.listFiles) { + if (!eachDir.isDirectory) { + if (eachDir.getName.endsWith(extension)) { + CarbonUtil.deleteFoldersAndFilesSilent(eachDir) + } + } else { + deleteIndexFile(eachDir.getPath, extension) + } + } + } + + //TO DO, need to remove segment dependency and tableIdentifier Dependency + test("read carbondata files (sdk Writer Output) using the SparkCarbonFileFormat ") { + buildTestData() + assert(new File(writerPath).exists()) + sql("DROP TABLE IF EXISTS sdkOutputTable") + + //data source file format + if (SparkUtil.isSparkVersionEqualTo("2.1")) { + //data source file format + sql(s"""CREATE TABLE sdkOutputTable USING carbon OPTIONS (PATH '$writerPath') """) + } else if (SparkUtil.isSparkVersionXandAbove("2.2")) { + //data source file format + sql( + s"""CREATE TABLE sdkOutputTable USING carbon LOCATION + |'$writerPath' """.stripMargin) + } else{ + // TO DO + } + + sql("Describe formatted sdkOutputTable").show(false) --- End diff -- No need to use .show(). All these queries can be removed
---