Github user yhuai commented on a diff in the pull request: https://github.com/apache/spark/pull/14155#discussion_r75063676 --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala --- @@ -144,16 +161,147 @@ private[spark] class HiveExternalCatalog(client: HiveClient, hadoopConf: Configu assert(tableDefinition.identifier.database.isDefined) val db = tableDefinition.identifier.database.get requireDbExists(db) + verifyTableProperties(tableDefinition) + + if (tableDefinition.provider == Some("hive") || tableDefinition.tableType == VIEW) { + client.createTable(tableDefinition, ignoreIfExists) + } else { + val tableProperties = tableMetadataToProperties(tableDefinition) + + def newSparkSQLSpecificMetastoreTable(): CatalogTable = { + tableDefinition.copy( + schema = new StructType, + partitionColumnNames = Nil, + bucketSpec = None, + properties = tableDefinition.properties ++ tableProperties) + } + + def newHiveCompatibleMetastoreTable(serde: HiveSerDe, path: String): CatalogTable = { + tableDefinition.copy( + storage = tableDefinition.storage.copy( + locationUri = Some(new Path(path).toUri.toString), + inputFormat = serde.inputFormat, + outputFormat = serde.outputFormat, + serde = serde.serde + ), + properties = tableDefinition.properties ++ tableProperties) + } + + val qualifiedTableName = tableDefinition.identifier.quotedString + val maybeSerde = HiveSerDe.sourceToSerDe(tableDefinition.provider.get) + val maybePath = new CaseInsensitiveMap(tableDefinition.storage.properties).get("path") + val skipHiveMetadata = tableDefinition.storage.properties + .getOrElse("skipHiveMetadata", "false").toBoolean + + val (hiveCompatibleTable, logMessage) = (maybeSerde, maybePath) match { + case _ if skipHiveMetadata => + val message = + s"Persisting data source table $qualifiedTableName into Hive metastore in" + + "Spark SQL specific format, which is NOT compatible with Hive." + (None, message) + + // our bucketing is un-compatible with hive(different hash function) + case _ if tableDefinition.bucketSpec.nonEmpty => + val message = + s"Persisting bucketed data source table $qualifiedTableName into " + + "Hive metastore in Spark SQL specific format, which is NOT compatible with Hive. " + (None, message) + + case (Some(serde), Some(path)) => + val message = + s"Persisting data source table $qualifiedTableName with a single input path " + + s"into Hive metastore in Hive compatible format." + (Some(newHiveCompatibleMetastoreTable(serde, path)), message) + + case (Some(_), None) => + val message = + s"Data source table $qualifiedTableName is not file based. Persisting it into " + + s"Hive metastore in Spark SQL specific format, which is NOT compatible with Hive." + (None, message) + + case _ => + val provider = tableDefinition.provider.get + val message = + s"Couldn't find corresponding Hive SerDe for data source provider $provider. " + + s"Persisting data source table $qualifiedTableName into Hive metastore in " + + s"Spark SQL specific format, which is NOT compatible with Hive." + (None, message) + } + + (hiveCompatibleTable, logMessage) match { + case (Some(table), message) => + // We first try to save the metadata of the table in a Hive compatible way. + // If Hive throws an error, we fall back to save its metadata in the Spark SQL + // specific way. + try { + logInfo(message) + saveTableIntoHive(table, ignoreIfExists) + } catch { + case NonFatal(e) => + val warningMessage = + s"Could not persist ${tableDefinition.identifier.quotedString} in a Hive " + + "compatible way. Persisting it into Hive metastore in Spark SQL specific format." + logWarning(warningMessage, e) + saveTableIntoHive(newSparkSQLSpecificMetastoreTable(), ignoreIfExists) + } + + case (None, message) => + logWarning(message) + saveTableIntoHive(newSparkSQLSpecificMetastoreTable(), ignoreIfExists) + } + } + } + + private def tableMetadataToProperties(table: CatalogTable): Map[String, String] = { + val properties = new scala.collection.mutable.HashMap[String, String] + properties.put(DATASOURCE_PROVIDER, table.provider.get) + + // Serialized JSON schema string may be too long to be stored into a single metastore table + // property. In this case, we split the JSON string and store each part as a separate table + // property. + val threshold = 4000 + val schemaJsonString = table.schema.json + // Split the JSON string. + val parts = schemaJsonString.grouped(threshold).toSeq + properties.put(DATASOURCE_SCHEMA_NUMPARTS, parts.size.toString) + parts.zipWithIndex.foreach { case (part, index) => + properties.put(s"$DATASOURCE_SCHEMA_PART_PREFIX$index", part) + } + + if (table.partitionColumnNames.nonEmpty) { + properties.put(DATASOURCE_SCHEMA_NUMPARTCOLS, table.partitionColumnNames.length.toString) + table.partitionColumnNames.zipWithIndex.foreach { case (partCol, index) => + properties.put(s"$DATASOURCE_SCHEMA_PARTCOL_PREFIX$index", partCol) + } + } + + if (table.bucketSpec.isDefined) { + val BucketSpec(numBuckets, bucketColumnNames, sortColumnNames) = table.bucketSpec.get + + properties.put(DATASOURCE_SCHEMA_NUMBUCKETS, numBuckets.toString) + properties.put(DATASOURCE_SCHEMA_NUMBUCKETCOLS, bucketColumnNames.length.toString) + bucketColumnNames.zipWithIndex.foreach { case (bucketCol, index) => + properties.put(s"$DATASOURCE_SCHEMA_BUCKETCOL_PREFIX$index", bucketCol) + } + + if (sortColumnNames.nonEmpty) { + properties.put(DATASOURCE_SCHEMA_NUMSORTCOLS, sortColumnNames.length.toString) + sortColumnNames.zipWithIndex.foreach { case (sortCol, index) => + properties.put(s"$DATASOURCE_SCHEMA_SORTCOL_PREFIX$index", sortCol) + } + } + } + + properties.toMap + } - if ( + private def saveTableIntoHive(tableDefinition: CatalogTable, ignoreIfExists: Boolean): Unit = { // If this is an external data source table... - tableDefinition.properties.contains("spark.sql.sources.provider") && - tableDefinition.tableType == CatalogTableType.EXTERNAL && - // ... that is not persisted as Hive compatible format (external tables in Hive compatible - // format always set `locationUri` to the actual data location and should NOT be hacked as - // following.) - tableDefinition.storage.locationUri.isEmpty - ) { + if (tableDefinition.tableType == EXTERNAL && + // ... that is not persisted as Hive compatible format (external tables in Hive compatible + // format always set `locationUri` to the actual data location and should NOT be hacked as + // following.) + tableDefinition.storage.locationUri.isEmpty) { --- End diff -- We should still check `spark.sql.sources.provider`, right?
--- 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