yyanyy commented on a change in pull request #2560:
URL: https://github.com/apache/iceberg/pull/2560#discussion_r628533052
##########
File path:
spark3-extensions/src/main/antlr/org.apache.spark.sql.catalyst.parser.extensions/IcebergSqlExtensions.g4
##########
@@ -71,6 +71,8 @@ statement
| ALTER TABLE multipartIdentifier DROP PARTITION FIELD transform
#dropPartitionField
| ALTER TABLE multipartIdentifier REPLACE PARTITION FIELD transform WITH
transform (AS name=identifier)? #replacePartitionField
| ALTER TABLE multipartIdentifier WRITE writeSpec
#setWriteDistributionAndOrdering
+ | ALTER TABLE multipartIdentifier REPLACE ROW_IDENTIFIER FIELDS '('
fields+=identifier (',' fields+=identifier)* ')' #replaceIdentifierFields
Review comment:
do we now have `SET ROW_IDENTIFIER`? if not, wondering if it would seem
odd if user can only "replace" even when the table doesn't have row identifiers
yet
##########
File path:
spark3-extensions/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ReplaceIdentifierFieldsExec.scala
##########
@@ -0,0 +1,52 @@
+/*
+ * 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.iceberg.spark.source.SparkTable
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions.Attribute
+import org.apache.spark.sql.connector.catalog.Identifier
+import org.apache.spark.sql.connector.catalog.TableCatalog
+
+case class ReplaceIdentifierFieldsExec(
+ catalog: TableCatalog,
+ ident: Identifier,
+ fields: Seq[String]) extends V2CommandExec {
+ import org.apache.spark.sql.connector.catalog.CatalogV2Implicits._
+
+ override lazy val output: Seq[Attribute] = Nil
+
+ override protected def run(): Seq[InternalRow] = {
+ catalog.loadTable(ident) match {
+ case iceberg: SparkTable =>
+ iceberg.table.updateSchema()
+
.setIdentifierFields(scala.collection.JavaConverters.seqAsJavaList(fields))
Review comment:
not familiar with this code base, curious - is it possible that input
`fields` is null here and we encounter NPE? If it's nullable and NPE safe, do
we want `replace` with empty input to be the same as `drop`?
##########
File path:
spark3-extensions/src/test/java/org/apache/iceberg/spark/extensions/TestAlterTableSchema.java
##########
@@ -0,0 +1,85 @@
+/*
+ * 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.iceberg.spark.extensions;
+
+import java.util.Map;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.relocated.com.google.common.collect.Sets;
+import org.junit.After;
+import org.junit.Assert;
+import org.junit.Test;
+
+public class TestAlterTableSchema extends SparkExtensionsTestBase {
Review comment:
great to see this!
--
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
