Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/14155#discussion_r74684229 --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveExternalCatalog.scala --- @@ -144,16 +161,141 @@ 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 provider = tableDefinition.provider.get + val partitionColumns = tableDefinition.partitionColumnNames + val bucketSpec = tableDefinition.bucketSpec + + val tableProperties = new scala.collection.mutable.HashMap[String, String] + tableProperties.put(DATASOURCE_PROVIDER, provider) + + // 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 = tableDefinition.schema.json + // Split the JSON string. + val parts = schemaJsonString.grouped(threshold).toSeq + tableProperties.put(DATASOURCE_SCHEMA_NUMPARTS, parts.size.toString) + parts.zipWithIndex.foreach { case (part, index) => + tableProperties.put(s"$DATASOURCE_SCHEMA_PART_PREFIX$index", part) + } + + if (partitionColumns.nonEmpty) { + tableProperties.put(DATASOURCE_SCHEMA_NUMPARTCOLS, partitionColumns.length.toString) + partitionColumns.zipWithIndex.foreach { case (partCol, index) => + tableProperties.put(s"$DATASOURCE_SCHEMA_PARTCOL_PREFIX$index", partCol) + } + } + + if (bucketSpec.isDefined) { + val BucketSpec(numBuckets, bucketColumnNames, sortColumnNames) = bucketSpec.get + + tableProperties.put(DATASOURCE_SCHEMA_NUMBUCKETS, numBuckets.toString) + tableProperties.put(DATASOURCE_SCHEMA_NUMBUCKETCOLS, bucketColumnNames.length.toString) + bucketColumnNames.zipWithIndex.foreach { case (bucketCol, index) => + tableProperties.put(s"$DATASOURCE_SCHEMA_BUCKETCOL_PREFIX$index", bucketCol) + } + + if (sortColumnNames.nonEmpty) { + tableProperties.put(DATASOURCE_SCHEMA_NUMSORTCOLS, sortColumnNames.length.toString) + sortColumnNames.zipWithIndex.foreach { case (sortCol, index) => + tableProperties.put(s"$DATASOURCE_SCHEMA_SORTCOL_PREFIX$index", sortCol) + } + } + } + + def newSparkSQLSpecificMetastoreTable(): CatalogTable = { + CatalogTable( + identifier = tableDefinition.identifier, + tableType = tableDefinition.tableType, + storage = tableDefinition.storage, + schema = new StructType(), + properties = tableDefinition.properties ++ tableProperties.toMap) + } + + def newHiveCompatibleMetastoreTable(serde: HiveSerDe, path: String): CatalogTable = { + tableDefinition.copy(properties = tableProperties.toMap).withNewStorage( + locationUri = Some(new Path(path).toUri.toString), + inputFormat = serde.inputFormat, + outputFormat = serde.outputFormat, + serde = serde.serde) + } + + val qualifiedTableName = tableDefinition.identifier.quotedString + val maybePath = new CaseInsensitiveMap(tableDefinition.storage.properties).get("path") --- End diff -- Previous code create a `DataSource` and resolve it, just to get the paths for this data source. We can get the path from data source options directly.
--- 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