Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/16944#discussion_r103067980
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala ---
@@ -161,22 +164,51 @@ private[hive] class
HiveMetastoreCatalog(sparkSession: SparkSession) extends Log
bucketSpec,
Some(partitionSchema))
+ val catalogTable = metastoreRelation.catalogTable
val logicalRelation = cached.getOrElse {
val sizeInBytes =
metastoreRelation.stats(sparkSession.sessionState.conf).sizeInBytes.toLong
val fileIndex = {
- val index = new CatalogFileIndex(
- sparkSession, metastoreRelation.catalogTable, sizeInBytes)
+ val index = new CatalogFileIndex(sparkSession, catalogTable,
sizeInBytes)
if (lazyPruningEnabled) {
index
} else {
index.filterPartitions(Nil) // materialize all the
partitions in memory
}
}
val partitionSchemaColumnNames =
partitionSchema.map(_.name.toLowerCase).toSet
- val dataSchema =
- StructType(metastoreSchema
- .filterNot(field =>
partitionSchemaColumnNames.contains(field.name.toLowerCase)))
+ val filteredMetastoreSchema = StructType(metastoreSchema
+ .filterNot(field =>
partitionSchemaColumnNames.contains(field.name.toLowerCase)))
+
+ val inferenceMode =
sparkSession.sessionState.conf.caseSensitiveInferenceMode
+ val shouldInfer = (inferenceMode != NEVER_INFER) &&
!catalogTable.schemaPreservesCase
+
+ val (dataSchema, updatedTable) = if (shouldInfer) {
+ logInfo(s"Inferring case-sensitive schema for table $tableName
(inference mode: " +
+ s"$inferenceMode)")
+ val inferredSchema
+ = inferSchema(metastoreSchema, options, defaultSource,
fileType, fileIndex)
+
+ // If configured, save the inferred case-sensitive schema to
the table properties and
+ // fetch the updated CatalogTable record for use in the
LogicalRelation.
+ val updatedTable = if (inferenceMode == INFER_AND_SAVE) {
+ updateCatalogTable(catalogTable, inferredSchema).getOrElse {
+ logWarning(s"Unable to save case-sensitive schema for
table $tableName " +
+ s"(inference mode: $inferenceMode)")
+ catalogTable
+ }
+ } else {
+ catalogTable
+ }
+ val schema = inferredSchema.getOrElse {
--- End diff --
Should we put this before `updatedTable` above? If the schema is unable to
be inferred, we don't need to update the table.
---
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
