Skip to content

[SPARK-19611][SQL][followup] set dataSchema correctly in HiveMetastoreCatalog.convertToLogicalRelation #19615

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
cloud-fan wants to merge 1 commit into from
Closed

[SPARK-19611][SQL][followup] set dataSchema correctly in HiveMetastoreCatalog.convertToLogicalRelation #19615

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 11 additions & 11 deletions sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,13 +164,12 @@ private[hive] class HiveMetastoreCatalog(sparkSession: SparkSession) extends Log
}
}

val (dataSchema, updatedTable) =
inferIfNeeded(relation, options, fileFormat, Option(fileIndex))
val updatedTable = inferIfNeeded(relation, options, fileFormat, Option(fileIndex))
Copy link
Member

@viirya viirya Oct 31, 2017

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeah, we missed this. Actually the variable name is indicating it is data schema...


val fsRelation = HadoopFsRelation(
location = fileIndex,
partitionSchema = partitionSchema,
dataSchema = dataSchema,
dataSchema = updatedTable.dataSchema,
bucketSpec = None,
fileFormat = fileFormat,
options = options)(sparkSession = sparkSession)
Expand All @@ -191,13 +190,13 @@ private[hive] class HiveMetastoreCatalog(sparkSession: SparkSession) extends Log
fileFormatClass,
None)
val logicalRelation = cached.getOrElse {
val (dataSchema, updatedTable) = inferIfNeeded(relation, options, fileFormat)
val updatedTable = inferIfNeeded(relation, options, fileFormat)
val created =
LogicalRelation(
DataSource(
sparkSession = sparkSession,
paths = rootPath.toString :: Nil,
userSpecifiedSchema = Option(dataSchema),
userSpecifiedSchema = Option(updatedTable.dataSchema),
bucketSpec = None,
options = options,
className = fileType).resolveRelation(),
Expand All @@ -224,7 +223,7 @@ private[hive] class HiveMetastoreCatalog(sparkSession: SparkSession) extends Log
relation: HiveTableRelation,
options: Map[String, String],
fileFormat: FileFormat,
fileIndexOpt: Option[FileIndex] = None): (StructType, CatalogTable) = {
fileIndexOpt: Option[FileIndex] = None): CatalogTable = {
val inferenceMode = sparkSession.sessionState.conf.caseSensitiveInferenceMode
val shouldInfer = (inferenceMode != NEVER_INFER) && !relation.tableMeta.schemaPreservesCase
val tableName = relation.tableMeta.identifier.unquotedString
Expand All @@ -241,21 +240,22 @@ private[hive] class HiveMetastoreCatalog(sparkSession: SparkSession) extends Log
sparkSession,
options,
fileIndex.listFiles(Nil, Nil).flatMap(_.files))
.map(mergeWithMetastoreSchema(relation.tableMeta.schema, _))
.map(mergeWithMetastoreSchema(relation.tableMeta.dataSchema, _))

inferredSchema match {
case Some(schema) =>
case Some(dataSchema) =>
val schema = StructType(dataSchema ++ relation.tableMeta.partitionSchema)
if (inferenceMode == INFER_AND_SAVE) {
updateCatalogSchema(relation.tableMeta.identifier, schema)
}
(schema, relation.tableMeta.copy(schema = schema))
relation.tableMeta.copy(schema = schema)
case None =>
logWarning(s"Unable to infer schema for table $tableName from file format " +
s"$fileFormat (inference mode: $inferenceMode). Using metastore schema.")
(relation.tableMeta.schema, relation.tableMeta)
relation.tableMeta
}
} else {
(relation.tableMeta.schema, relation.tableMeta)
relation.tableMeta
}
}

Expand Down