cloud-fan commented on a change in pull request #33432:
URL: https://github.com/apache/spark/pull/33432#discussion_r709337374
##########
File path:
sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala
##########
@@ -158,14 +161,22 @@ private[hive] class HiveMetastoreCatalog(sparkSession:
SparkSession) extends Log
relation: HiveTableRelation,
options: Map[String, String],
fileFormatClass: Class[_ <: FileFormat],
- fileType: String): LogicalRelation = {
+ fileType: String,
+ isWrite: Boolean): LogicalRelation = {
val metastoreSchema = relation.tableMeta.schema
val tableIdentifier =
QualifiedTableName(relation.tableMeta.database,
relation.tableMeta.identifier.table)
val lazyPruningEnabled =
sparkSession.sqlContext.conf.manageFilesourcePartitions
val tablePath = new Path(relation.tableMeta.location)
val fileFormat = fileFormatClass.getConstructor().newInstance()
+ val bucketSpec = relation.tableMeta.bucketSpec
+ val (hiveOptions, hiveBucketSpec) =
+ if (isWrite) {
+ (options.updated(DDLUtils.HIVE_PROVIDER, "true"), bucketSpec)
Review comment:
`DDLUtils.HIVE_PROVIDER` is `hive`, which may conflict with
user-provided options.
Shall we use a more internal name like
`__hive_compatible_bucketed_table_insertion__`?
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
