Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/12645#discussion_r60838889
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/command/createDataSourceTables.scala
---
@@ -0,0 +1,452 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.command
+
+import java.util.regex.Pattern
+
+import scala.collection.mutable
+import scala.util.control.NonFatal
+
+import org.apache.spark.internal.Logging
+import org.apache.spark.sql._
+import org.apache.spark.sql.catalyst.TableIdentifier
+import org.apache.spark.sql.catalyst.analysis.EliminateSubqueryAliases
+import org.apache.spark.sql.catalyst.catalog.{CatalogColumn,
CatalogStorageFormat, CatalogTable, CatalogTableType}
+import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
+import org.apache.spark.sql.execution.datasources.{BucketSpec, DataSource,
HadoopFsRelation, LogicalRelation}
+import org.apache.spark.sql.internal.HiveSerDe
+import org.apache.spark.sql.sources.InsertableRelation
+import org.apache.spark.sql.types._
+
+/**
+ * A command used to create a data source table.
+ *
+ * Note: This is different from [[CreateTable]]. Please check the syntax
for difference.
+ * This is not intended for temporary tables.
+ *
+ * The syntax of using this command in SQL is:
+ * {{{
+ * CREATE TABLE [IF NOT EXISTS] [db_name.]table_name
+ * [(col1 data_type [COMMENT col_comment], ...)]
+ * USING format OPTIONS ([option1_name "option1_value", option2_name
"option2_value", ...])
+ * }}}
+ */
+case class CreateDataSourceTableCommand(
+ tableIdent: TableIdentifier,
+ userSpecifiedSchema: Option[StructType],
+ provider: String,
+ options: Map[String, String],
+ ignoreIfExists: Boolean,
+ managedIfNoPath: Boolean)
+ extends RunnableCommand {
+
+ override def run(sqlContext: SQLContext): Seq[Row] = {
+ // Since we are saving metadata to metastore, we need to check if
metastore supports
+ // the table name and database name we have for this query.
MetaStoreUtils.validateName
+ // is the method used by Hive to check if a table name or a database
name is valid for
+ // the metastore.
+ if (!CreateDataSourceTableUtils.validateName(tableIdent.table)) {
+ throw new AnalysisException(s"Table name ${tableIdent.table} is not
a valid name for " +
+ s"metastore. Metastore only accepts table name containing
characters, numbers and _.")
+ }
+ if (tableIdent.database.isDefined &&
+ !CreateDataSourceTableUtils.validateName(tableIdent.database.get)) {
+ throw new AnalysisException(s"Database name
${tableIdent.database.get} is not a valid name " +
+ s"for metastore. Metastore only accepts database name containing "
+
+ s"characters, numbers and _.")
+ }
+
+ val tableName = tableIdent.unquotedString
+ val sessionState = sqlContext.sessionState
+
+ if (sessionState.catalog.tableExists(tableIdent)) {
+ if (ignoreIfExists) {
+ return Seq.empty[Row]
+ } else {
+ throw new AnalysisException(s"Table $tableName already exists.")
+ }
+ }
+
+ var isExternal = true
+ val optionsWithPath =
+ if (!options.contains("path") && managedIfNoPath) {
+ isExternal = false
+ options + ("path" ->
sessionState.catalog.defaultTablePath(tableIdent))
+ } else {
+ options
+ }
+
+ // Create the relation to validate the arguments before writing the
metadata to the metastore.
+ DataSource(
+ sqlContext = sqlContext,
+ userSpecifiedSchema = userSpecifiedSchema,
+ className = provider,
+ bucketSpec = None,
+ options = optionsWithPath).resolveRelation()
+
+ CreateDataSourceTableUtils.createDataSourceTable(
+ sqlContext = sqlContext,
+ tableIdent = tableIdent,
+ userSpecifiedSchema = userSpecifiedSchema,
+ partitionColumns = Array.empty[String],
+ bucketSpec = None,
+ provider = provider,
+ options = optionsWithPath,
+ isExternal = isExternal)
+
+ Seq.empty[Row]
+ }
+}
+
+/**
+ * A command used to create a data source table using the result of a
query.
+ *
+ * Note: This is different from [[CreateTableAsSelect]]. Please check the
syntax for difference.
+ * This is not intended for temporary tables.
+ *
+ * The syntax of using this command in SQL is:
+ * {{{
+ * CREATE TABLE [IF NOT EXISTS] [db_name.]table_name
+ * USING format OPTIONS ([option1_name "option1_value", option2_name
"option2_value", ...])
+ * AS SELECT ...
+ * }}}
+ */
+case class CreateDataSourceTableAsSelectCommand(
+ tableIdent: TableIdentifier,
+ provider: String,
+ partitionColumns: Array[String],
--- End diff --
you don't need to do this now, but i think it'd maybe make more sense to
just pass a single CatalogTable in, with "mode" and query.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
