SaurabhChawla100 commented on a change in pull request #29045:
URL: https://github.com/apache/spark/pull/29045#discussion_r454515273
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcFileFormat.scala
##########
@@ -160,12 +160,12 @@ class OrcFileFormat
}
val resultSchema = StructType(requiredSchema.fields ++
partitionSchema.fields)
+ val actualSchema = StructType(dataSchema.fields ++ partitionSchema.fields)
val sqlConf = sparkSession.sessionState.conf
val enableVectorizedReader = supportBatch(sparkSession, resultSchema)
val capacity = sqlConf.orcVectorizedReaderBatchSize
- val resultSchemaString = OrcUtils.orcTypeDescriptionString(resultSchema)
- OrcConf.MAPRED_INPUT_SCHEMA.setString(hadoopConf, resultSchemaString)
Review comment:
@cloud-fan - Do we need to make the similar change in these file
OrcPartitionReaderFactory
override def buildReader(file: PartitionedFile):
PartitionReader[InternalRow] = {
and
override def buildColumnarReader(file: PartitionedFile):
PartitionReader[ColumnarBatch] = {
----------------------------------------------------------------
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:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
