Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/14537#discussion_r76189247 --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala --- @@ -237,21 +237,27 @@ 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 schema = fileType match { + case "parquet" => + val inferredSchema = + defaultSource.inferSchema(sparkSession, options, fileCatalog.allFiles()) + + // For Parquet, get correct schema by merging Metastore schema data types --- End diff -- Do we have a test for this feature? I think we should make them consistent, i.e. parquet conversions should also use the metastore schema. cc @yhuai @liancheng
--- 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