[GitHub] [spark] rdblue commented on a change in pull request #29339: [Spark-32512][SQL][WIP] add alter table add/drop partition command for datasourcev2
rdblue commented on a change in pull request #29339:
URL: https://github.com/apache/spark/pull/29339#discussion_r464546037
##
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,
Review comment:
Why not pass a `Table` instance like other plans that modify table data
(e.g., `AppendDataExec`)?
We generally like to load tables early, so that we can do as much validation
as possible in the analyzer and planner. By loading the table before passing it
here, we would be able to use analyzer rules to validate the partition specs
against the table's partition schema, and to make sure the table implements
`SupportsPartitions`.
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] rdblue commented on a change in pull request #29339: [Spark-32512][SQL][WIP] add alter table add/drop partition command for datasourcev2
rdblue commented on a change in pull request #29339:
URL: https://github.com/apache/spark/pull/29339#discussion_r464541802
##
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:
Conversion to `InternalRow` should not modify the partition values by
filling in defaults. Filling in a default like this is a correctness bug.
I think this should require that all partition names are present in the map,
and pass null if a name is present but does not have a value. If the partition
doesn't allow null partition values, then it should throw an exception.
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] rdblue commented on a change in pull request #29339: [Spark-32512][SQL][WIP] add alter table add/drop partition command for datasourcev2
rdblue commented on a change in pull request #29339:
URL: https://github.com/apache/spark/pull/29339#discussion_r464539922
##
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:
Why is this included with the implicits when it isn't an implicit class?
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] rdblue commented on a change in pull request #29339: [Spark-32512][SQL][WIP] add alter table add/drop partition command for datasourcev2
rdblue commented on a change in pull request #29339:
URL: https://github.com/apache/spark/pull/29339#discussion_r464539202
##
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)
+
+ val conflictKeys = spec.keys.filterNot(partNames.contains)
+ if (conflictKeys.nonEmpty) {
+throw new AnalysisException(
+ s"Partition key ${conflictKeys.mkString(",")} " +
+s"not exists in ${ident.namespace().quoted}.${ident.name()}")
Review comment:
Nit: indentation doesn't match between these lines.
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] rdblue commented on a change in pull request #29339: [Spark-32512][SQL][WIP] add alter table add/drop partition command for datasourcev2
rdblue commented on a change in pull request #29339:
URL: https://github.com/apache/spark/pull/29339#discussion_r464539078
##
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:
Why is this added to the partition parameters? I think Spark should
handle this by ignoring `PartitionAlreadyExistsException` like we do in other
cases.
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
