Github user viirya commented on a diff in the pull request: https://github.com/apache/spark/pull/16944#discussion_r101456890 --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveMetastoreCatalog.scala --- @@ -161,23 +161,49 @@ 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 + val filteredMetastoreSchema = StructType(metastoreSchema .filterNot(field => partitionSchemaColumnNames.contains(field.name.toLowerCase))) + val inferenceMode = sparkSession.sessionState.conf.schemaInferenceMode + val dataSchema = if (inferenceMode != "NEVER_INFER" && + !catalogTable.schemaFromTableProps) { + val fileStatuses = fileIndex.listFiles(Nil).flatMap(_.files) + val inferred = defaultSource.inferSchema(sparkSession, options, fileStatuses) + val merged = if (fileType.equals("parquet")) { + inferred.map(ParquetFileFormat.mergeMetastoreParquetSchema(metastoreSchema, _)) + } else { + inferred + } + if (inferenceMode == "INFER_AND_SAVE") { + // If a case-sensitive schema was successfully inferred, execute an alterTable + // operation to save the schema to the table properties. + merged.foreach { mergedSchema => + val updatedTable = catalogTable.copy(schema = mergedSchema) --- End diff -- Wrong indent style.
--- 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