cloud-fan commented on a change in pull request #16944:
URL: https://github.com/apache/spark/pull/16944#discussion_r443343602
##########
File path:
sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala
##########
@@ -218,6 +228,54 @@ private[hive] class HiveMetastoreCatalog(sparkSession:
SparkSession) extends Log
result.copy(expectedOutputAttributes = Some(relation.output))
}
+ private def inferIfNeeded(
+ relation: CatalogRelation,
+ options: Map[String, String],
+ fileFormat: FileFormat,
+ fileIndexOpt: Option[FileIndex] = None): (StructType, CatalogTable) = {
+ val inferenceMode =
sparkSession.sessionState.conf.caseSensitiveInferenceMode
+ val shouldInfer = (inferenceMode != NEVER_INFER) &&
!relation.tableMeta.schemaPreservesCase
+ val tableName = relation.tableMeta.identifier.unquotedString
+ if (shouldInfer) {
+ logInfo(s"Inferring case-sensitive schema for table $tableName
(inference mode: " +
+ s"$inferenceMode)")
+ val fileIndex = fileIndexOpt.getOrElse {
+ val rootPath = new Path(relation.tableMeta.location)
+ new InMemoryFileIndex(sparkSession, Seq(rootPath), options, None)
+ }
+
+ val inferredSchema = fileFormat
+ .inferSchema(
+ sparkSession,
+ options,
+ fileIndex.listFiles(Nil).flatMap(_.files))
Review comment:
schema inference needs to look at the entire data set.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
