Github user yhuai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14207#discussion_r73940468
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/command/createDataSourceTables.scala
---
@@ -95,17 +95,39 @@ case class CreateDataSourceTableCommand(
}
// Create the relation to validate the arguments before writing the
metadata to the metastore.
- DataSource(
- sparkSession = sparkSession,
- userSpecifiedSchema = userSpecifiedSchema,
- className = provider,
- bucketSpec = None,
- options = optionsWithPath).resolveRelation(checkPathExist = false)
+ val dataSource: BaseRelation =
+ DataSource(
+ sparkSession = sparkSession,
+ userSpecifiedSchema = userSpecifiedSchema,
+ className = provider,
+ bucketSpec = None,
+ options = optionsWithPath).resolveRelation(checkPathExist = false)
+
+ val partitionColumns = if (userSpecifiedSchema.nonEmpty) {
+ userSpecifiedPartitionColumns
+ } else {
+ val res = dataSource match {
+ case r: HadoopFsRelation => r.partitionSchema.fieldNames
+ case _ => Array.empty[String]
+ }
+ if (userSpecifiedPartitionColumns.length > 0) {
+ // The table does not have a specified schema, which means that
the schema will be inferred
+ // when we load the table. So, we are not expecting partition
columns and we will discover
+ // partitions when we load the table. However, if there are
specified partition columns,
+ // we simply ignore them and provide a warning message.
+ logWarning(
+ s"Specified partition columns
(${userSpecifiedPartitionColumns.mkString(",")}) will be " +
+ s"ignored. The schema and partition columns of table
$tableIdent are inferred. " +
+ s"Schema: ${dataSource.schema.simpleString}; " +
+ s"Partition columns: ${res.mkString("(", ", ", ")")}")
+ }
+ res
+ }
CreateDataSourceTableUtils.createDataSourceTable(
sparkSession = sparkSession,
tableIdent = tableIdent,
- userSpecifiedSchema = userSpecifiedSchema,
+ schema = dataSource.schema,
--- End diff --
seems we should still use the user-specified schema, right?
---
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
