[GitHub] [spark] stczwd commented on a change in pull request #29339: [Spark-32512][SQL][WIP] add alter table add/drop partition command for datasourcev2
stczwd commented on a change in pull request #29339:
URL: https://github.com/apache/spark/pull/29339#discussion_r465425990
##
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/AlterTableDropPartitionExec.scala
##
@@ -0,0 +1,58 @@
+/*
+ * 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.datasources.v2
+
+import org.apache.spark.sql.AnalysisException
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.catalog.CatalogTypes.TablePartitionSpec
+import org.apache.spark.sql.catalyst.expressions.Attribute
+import org.apache.spark.sql.connector.catalog.{CatalogV2Implicits, Identifier,
TableCatalog}
+
+/**
+ * Physical plan node for dropping partitions of table.
+ */
+case class AlterTableDropPartitionExec(
+catalog: TableCatalog,
+ident: Identifier,
+specs: Seq[TablePartitionSpec],
+ignoreIfNotExists: Boolean,
+purge: Boolean,
+retainData: Boolean) extends V2CommandExec {
Review comment:
I have give a warning for `purge`.
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] [spark] stczwd commented on a change in pull request #29339: [Spark-32512][SQL][WIP] add alter table add/drop partition command for datasourcev2
stczwd commented on a change in pull request #29339:
URL: https://github.com/apache/spark/pull/29339#discussion_r465015925
##
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/AlterTableDropPartitionExec.scala
##
@@ -0,0 +1,58 @@
+/*
+ * 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.datasources.v2
+
+import org.apache.spark.sql.AnalysisException
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.catalog.CatalogTypes.TablePartitionSpec
+import org.apache.spark.sql.catalyst.expressions.Attribute
+import org.apache.spark.sql.connector.catalog.{CatalogV2Implicits, Identifier,
TableCatalog}
+
+/**
+ * Physical plan node for dropping partitions of table.
+ */
+case class AlterTableDropPartitionExec(
+catalog: TableCatalog,
+ident: Identifier,
+specs: Seq[TablePartitionSpec],
+ignoreIfNotExists: Boolean,
+purge: Boolean,
+retainData: Boolean) extends V2CommandExec {
Review comment:
These two configurations seem to be mainly used in the hive tables.
Besides, the `retainData` is always false, and `purge` only works in some
versions.
Maybe put then into `table properties`? AFAIT, it the table that define
these operations.
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] [spark] stczwd commented on a change in pull request #29339: [Spark-32512][SQL][WIP] add alter table add/drop partition command for datasourcev2
stczwd commented on a change in pull request #29339:
URL: https://github.com/apache/spark/pull/29339#discussion_r464803576
##
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Implicits.scala
##
@@ -62,4 +74,31 @@ object DataSourceV2Implicits {
new CaseInsensitiveStringMap(options.asJava)
}
}
+
+ def convertPartitionIndentifers(
+ partSpec: TablePartitionSpec,
+ partSchema: StructType): InternalRow = {
Review comment:
Hm, a little ugly to me if it defined with implicits. I can change it if
you think it's better with implicits.
##
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/AlterTableAddPartitionExec.scala
##
@@ -0,0 +1,61 @@
+/*
+ * 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.datasources.v2
+
+import org.apache.spark.sql.AnalysisException
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.catalog.CatalogTypes.TablePartitionSpec
+import org.apache.spark.sql.catalyst.expressions.Attribute
+import org.apache.spark.sql.connector.catalog.{CatalogV2Implicits, Identifier,
TableCatalog}
+
+/**
+ * Physical plan node for adding partitions of table.
+ */
+case class AlterTableAddPartitionExec(
+catalog: TableCatalog,
+ident: Identifier,
+partitionSpecsAndLocs: Seq[(TablePartitionSpec, Option[String])],
+ignoreIfExists: Boolean) extends V2CommandExec {
+ import DataSourceV2Implicits._
+ import CatalogV2Implicits._
+
+ override def output: Seq[Attribute] = Seq.empty
+
+ override protected def run(): Seq[InternalRow] = {
+val table = catalog.loadTable(ident).asPartitionable
+val partNames = table.partitionSchema().map(_.name)
+
+partitionSpecsAndLocs.foreach { case (spec, location) =>
+ val partParams = new java.util.HashMap[String,
String](table.properties())
+ location.foreach(locationUri =>
+partParams.put("location", locationUri))
+ partParams.put("ignoreIfExists", ignoreIfExists.toString)
Review comment:
Fine, I change it.
##
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Implicits.scala
##
@@ -62,4 +74,31 @@ object DataSourceV2Implicits {
new CaseInsensitiveStringMap(options.asJava)
}
}
+
+ def convertPartitionIndentifers(
+ partSpec: TablePartitionSpec,
+ partSchema: StructType): InternalRow = {
+val partValues = partSchema.map { part =>
+ part.dataType match {
+case _: ByteType =>
+ partSpec.getOrElse(part.name, "0").toByte
Review comment:
sure. sounds reasonable to me.
##
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/AlterTableAddPartitionExec.scala
##
@@ -0,0 +1,61 @@
+/*
+ * 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.datasources.v2
+
+import org.apache.spark.sql.AnalysisException
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.catalog.CatalogTypes.TablePartitionSpec
+import org.apache.spark.sql.catalyst.expressions.Attribute
+import org.apache.spark.sql.connector.catalog.{CatalogV2Implicits, Identifier,
TableCatalog}
+
+/**
+ * Physical plan node for adding partitions of table.
+ */
+case class AlterTableAddPartitionExec(
+catalog: TableCatalog,
