Github user yhuai commented on a diff in the pull request:
https://github.com/apache/spark/pull/15024#discussion_r86272489
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala ---
@@ -189,66 +188,39 @@ private[spark] class HiveExternalCatalog(conf:
SparkConf, hadoopConf: Configurat
throw new TableAlreadyExistsException(db = db, table = table)
}
// Before saving data source table metadata into Hive metastore, we
should:
- // 1. Put table provider, schema, partition column names, bucket
specification and partition
- // provider in table properties.
+ // 1. Put table metadata like provider, schema, etc. in table
properties.
// 2. Check if this table is hive compatible
- // 2.1 If it's not hive compatible, set schema, partition columns
and bucket spec to empty
- // and save table metadata to Hive.
+ // 2.1 If it's not hive compatible, set location URI, schema,
partition columns and bucket
+ // spec to empty and save table metadata to Hive.
// 2.2 If it's hive compatible, set serde information in table
metadata and try to save
// it to Hive. If it fails, treat it as not hive compatible
and go back to 2.1
if (DDLUtils.isDatasourceTable(tableDefinition)) {
- // data source table always have a provider, it's guaranteed by
`DDLUtils.isDatasourceTable`.
- val provider = tableDefinition.provider.get
- val partitionColumns = tableDefinition.partitionColumnNames
- val bucketSpec = tableDefinition.bucketSpec
-
- val tableProperties = new scala.collection.mutable.HashMap[String,
String]
- tableProperties.put(DATASOURCE_PROVIDER, provider)
- if (tableDefinition.partitionProviderIsHive) {
- tableProperties.put(TABLE_PARTITION_PROVIDER, "hive")
- }
-
- // Serialized JSON schema string may be too long to be stored into a
single metastore table
- // property. In this case, we split the JSON string and store each
part as a separate table
- // property.
- val threshold = conf.get(SCHEMA_STRING_LENGTH_THRESHOLD)
- val schemaJsonString = tableDefinition.schema.json
- // Split the JSON string.
- val parts = schemaJsonString.grouped(threshold).toSeq
- tableProperties.put(DATASOURCE_SCHEMA_NUMPARTS, parts.size.toString)
- parts.zipWithIndex.foreach { case (part, index) =>
- tableProperties.put(s"$DATASOURCE_SCHEMA_PART_PREFIX$index", part)
- }
-
- if (partitionColumns.nonEmpty) {
- tableProperties.put(DATASOURCE_SCHEMA_NUMPARTCOLS,
partitionColumns.length.toString)
- partitionColumns.zipWithIndex.foreach { case (partCol, index) =>
- tableProperties.put(s"$DATASOURCE_SCHEMA_PARTCOL_PREFIX$index",
partCol)
- }
- }
-
- if (bucketSpec.isDefined) {
- val BucketSpec(numBuckets, bucketColumnNames, sortColumnNames) =
bucketSpec.get
+ val tableProperties = tableMetaToTableProps(tableDefinition)
- tableProperties.put(DATASOURCE_SCHEMA_NUMBUCKETS,
numBuckets.toString)
- tableProperties.put(DATASOURCE_SCHEMA_NUMBUCKETCOLS,
bucketColumnNames.length.toString)
- bucketColumnNames.zipWithIndex.foreach { case (bucketCol, index) =>
-
tableProperties.put(s"$DATASOURCE_SCHEMA_BUCKETCOL_PREFIX$index", bucketCol)
- }
-
- if (sortColumnNames.nonEmpty) {
- tableProperties.put(DATASOURCE_SCHEMA_NUMSORTCOLS,
sortColumnNames.length.toString)
- sortColumnNames.zipWithIndex.foreach { case (sortCol, index) =>
-
tableProperties.put(s"$DATASOURCE_SCHEMA_SORTCOL_PREFIX$index", sortCol)
- }
- }
+ val needDefaultTableLocation = tableDefinition.tableType == MANAGED
&&
+ tableDefinition.storage.locationUri.isEmpty
--- End diff --
Explain when the table is managed but the location uri is not empty.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
