Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/12271#discussion_r59593820
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
---
@@ -675,34 +680,38 @@ private[hive] class HiveClientImpl(
private def toHiveTable(table: CatalogTable): HiveTable = {
val hiveTable = new HiveTable(table.database, table.identifier.table)
- // For EXTERNAL_TABLE/MANAGED_TABLE, we also need to set EXTERNAL
field in
- // the table properties accodringly. Otherwise, if EXTERNAL_TABLE is
the table type
- // but EXTERNAL field is not set, Hive metastore will change the type
to
- // MANAGED_TABLE (see
- //
metastore/src/java/org/apache/hadoop/hive/metastore/ObjectStore.java#L1095-L1105)
+ // For EXTERNAL_TABLE, we also need to set EXTERNAL field in the table
properties.
+ // Otherwise, Hive metastore will change the table to a MANAGED_TABLE.
+ //
(metastore/src/java/org/apache/hadoop/hive/metastore/ObjectStore.java#L1095-L1105)
hiveTable.setTableType(table.tableType match {
case CatalogTableType.EXTERNAL_TABLE =>
hiveTable.setProperty("EXTERNAL", "TRUE")
HiveTableType.EXTERNAL_TABLE
case CatalogTableType.MANAGED_TABLE =>
- hiveTable.setProperty("EXTERNAL", "FALSE")
HiveTableType.MANAGED_TABLE
case CatalogTableType.INDEX_TABLE => HiveTableType.INDEX_TABLE
case CatalogTableType.VIRTUAL_VIEW => HiveTableType.VIRTUAL_VIEW
})
- hiveTable.setFields(table.schema.map(toHiveColumn).asJava)
- hiveTable.setPartCols(table.partitionColumns.map(toHiveColumn).asJava)
+ // Note: In Hive the schema and partition columns must be disjoint sets
+ val (partCols, schema) = table.schema.map(toHiveColumn).partition { c
=>
+ table.partitionColumnNames.contains(c.getName)
+ }
+ hiveTable.setFields(schema.asJava)
+ hiveTable.setPartCols(partCols.asJava)
// TODO: set sort columns here too
+ hiveTable.setBucketCols(table.bucketColumnNames.asJava)
hiveTable.setOwner(conf.getUser)
hiveTable.setNumBuckets(table.numBuckets)
hiveTable.setCreateTime((table.createTime / 1000).toInt)
hiveTable.setLastAccessTime((table.lastAccessTime / 1000).toInt)
table.storage.locationUri.foreach { loc =>
shim.setDataLocation(hiveTable, loc) }
table.storage.inputFormat.map(toInputFormat).foreach(hiveTable.setInputFormatClass)
table.storage.outputFormat.map(toOutputFormat).foreach(hiveTable.setOutputFormatClass)
- table.storage.serde.foreach(hiveTable.setSerializationLib)
+ hiveTable.setSerializationLib(
+
table.storage.serde.getOrElse("org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"))
--- End diff --
Yeah, agree if you are talking about my case. : )
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
