Github user rajeshbalamohan commented on a diff in the pull request: https://github.com/apache/spark/pull/14537#discussion_r75902767 --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala --- @@ -237,21 +237,26 @@ private[hive] class HiveMetastoreCatalog(sparkSession: SparkSession) extends Log new Path(metastoreRelation.catalogTable.storage.locationUri.get), partitionSpec) - val inferredSchema = if (fileType.equals("parquet")) { - val inferredSchema = - defaultSource.inferSchema(sparkSession, options, fileCatalog.allFiles()) - inferredSchema.map { inferred => - ParquetFileFormat.mergeMetastoreParquetSchema(metastoreSchema, inferred) - }.getOrElse(metastoreSchema) - } else { - defaultSource.inferSchema(sparkSession, options, fileCatalog.allFiles()).get + val inferredSchema = + defaultSource.inferSchema(sparkSession, options, fileCatalog.allFiles()) + val schema = fileType match { + case "parquet" => + // For Parquet, get correct schema by merging Metastore schema data types + // and Parquet schema field names. + inferredSchema.map { schema => + ParquetFileFormat.mergeMetastoreParquetSchema(metastoreSchema, schema) + }.getOrElse(metastoreSchema) + case "orc" => + inferredSchema.getOrElse(metastoreSchema) + case _ => + inferredSchema.get --- End diff -- Not sure if exception has to be thrown in this case. Or just return null in this case?
--- 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