ravipesala commented on a change in pull request #3483: [CARBONDATA-3597] Support Merge for SCD and CCD scenarios
URL:
https://github.com/apache/carbondata/pull/3483#discussion_r361896891
##########
File path: integration/spark2/src/main/scala/org/apache/spark/sql/execution/command/mutation/merge/CarbonMergeDataSetCommand.scala
##########
@@ -0,0 +1,520 @@
+/*
+ * 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.spark.sql.execution.command.mutation.merge
+
+import java.util.UUID
+
+import scala.collection.JavaConverters._
+import scala.collection.mutable.ArrayBuffer
+
+import org.apache.hadoop.io.NullWritable
+import org.apache.hadoop.mapreduce.{JobID, TaskAttemptID, TaskID, TaskType}
+import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl
+import org.apache.spark.sql.{AnalysisException, CarbonDatasourceHadoopRelation, Column, DataFrame, Dataset, Row, SparkSession}
+import org.apache.spark.sql.catalyst.expressions.{Attribute, Expression, GenericRowWithSchema}
+import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
+import org.apache.spark.sql.execution.command.{DataCommand, ExecutionErrors}
+import org.apache.spark.sql.execution.datasources.LogicalRelation
+import org.apache.spark.sql.functions._
+import org.apache.spark.sql.hive.DistributionUtil
+import org.apache.spark.sql.types.{IntegerType, StringType, StructField}
+import org.apache.spark.sql.util.SparkSQLUtil
+import org.apache.spark.util.{AccumulatorContext, AccumulatorMetadata, LongAccumulator}
+
+import org.apache.carbondata.common.logging.LogServiceFactory
+import org.apache.carbondata.core.constants.CarbonCommonConstants
+import org.apache.carbondata.core.datamap.Segment
+import org.apache.carbondata.core.metadata.SegmentFileStore
+import org.apache.carbondata.core.metadata.schema.table.CarbonTable
+import org.apache.carbondata.core.mutate.CarbonUpdateUtil
+import org.apache.carbondata.core.statusmanager.{LoadMetadataDetails, SegmentStatus}
+import org.apache.carbondata.core.util.path.CarbonTablePath
+import org.apache.carbondata.hadoop.api.CarbonTableOutputFormat
+import org.apache.carbondata.hadoop.internal.ObjectArrayWritable
+import org.apache.carbondata.processing.loading.FailureCauses
+import org.apache.carbondata.processing.loading.model.{CarbonLoadModel, CarbonLoadModelBuilder}
+import org.apache.carbondata.processing.util.CarbonLoaderUtil
+
+/**
+ * This command will merge the data of source dataset to target dataset backed by carbon table.
+ * @param targetDsOri Target dataset to merge the data. This dataset should be backed by carbontable
+ * @param srcDS Source dataset, it can be any data.
+ * @param mergeMatches It contains the join condition and list match conditions to apply.
+ */
+case class CarbonMergeDataSetCommand(targetDsOri: Dataset[Row],
Review comment:
ok
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[hidden email]
With regards,
Apache Git Services
Locked
