amogh-jahagirdar commented on code in PR #9340: URL: https://github.com/apache/iceberg/pull/9340#discussion_r1434452595
########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/source/SparkView.java: ########## @@ -0,0 +1,133 @@ +/* + * 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.source; + +import static org.apache.iceberg.TableProperties.FORMAT_VERSION; + +import java.util.Map; +import java.util.Optional; +import java.util.Set; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.spark.SparkSchemaUtil; +import org.apache.iceberg.view.BaseView; +import org.apache.iceberg.view.View; +import org.apache.iceberg.view.ViewOperations; +import org.apache.spark.sql.types.StructType; + +public class SparkView implements org.apache.spark.sql.connector.catalog.View { + + private static final Set<String> RESERVED_PROPERTIES = + ImmutableSet.of("provider", "location", FORMAT_VERSION); + + private final View icebergView; + + public SparkView(View icebergView) { + this.icebergView = icebergView; + } + + public View view() { + return icebergView; + } + + @Override + public String name() { + return icebergView.toString(); Review Comment: I looked at BaseTable and BaseMetadataTable, their `toString` just delegates to `name`. I don't have an opinion for views beyond it should be consistent in terms of either it's a fully qualified relation name or not (so if the name() is fully qualified in Table it should be the same in view. Or if it's not fully qualified, it's the same in View) ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/source/SparkView.java: ########## @@ -0,0 +1,148 @@ +/* + * 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.source; + +import static org.apache.iceberg.TableProperties.FORMAT_VERSION; + +import java.util.Map; +import java.util.Set; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.spark.SparkSchemaUtil; +import org.apache.iceberg.types.Types; +import org.apache.iceberg.view.BaseView; +import org.apache.iceberg.view.SQLViewRepresentation; +import org.apache.iceberg.view.View; +import org.apache.iceberg.view.ViewOperations; +import org.apache.spark.sql.types.StructType; + +public class SparkView implements org.apache.spark.sql.connector.catalog.View { + + private static final Set<String> RESERVED_PROPERTIES = + ImmutableSet.of("provider", "location", FORMAT_VERSION); + + private final View icebergView; + private final String catalogName; + private StructType lazySchema = null; + + public SparkView(String catalogName, View icebergView) { + this.catalogName = catalogName; + this.icebergView = icebergView; + } + + public View view() { + return icebergView; + } + + @Override + public String name() { + return icebergView.toString(); + } + + @Override + public String query() { + SQLViewRepresentation sqlRepr = icebergView.sqlFor("spark"); + Preconditions.checkState(sqlRepr != null, "Cannot load SQL for view %s", name()); Review Comment: Is it possible to fail before we reach this case? I think we would know before creating the `SparkView` if for whatever reason there is no dialect. ########## spark/v3.5/spark-extensions/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveViews.scala: ########## @@ -0,0 +1,115 @@ +/* + * 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.catalyst.analysis + +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.parser.ParseException +import org.apache.spark.sql.catalyst.plans.logical.IcebergView +import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan +import org.apache.spark.sql.catalyst.plans.logical.SubqueryAlias +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.connector.catalog.{View => V2View} +import org.apache.spark.sql.connector.catalog.CatalogManager +import org.apache.spark.sql.connector.catalog.CatalogPlugin +import org.apache.spark.sql.connector.catalog.Identifier +import org.apache.spark.sql.connector.catalog.LookupCatalog +import org.apache.spark.sql.connector.catalog.View +import org.apache.spark.sql.connector.catalog.ViewCatalog +import org.apache.spark.sql.errors.QueryCompilationErrors + +case class ResolveViews(spark: SparkSession) extends Rule[LogicalPlan] with LookupCatalog { + + import org.apache.spark.sql.connector.catalog.CatalogV2Implicits._ + + protected lazy val catalogManager: CatalogManager = spark.sessionState.catalogManager + + override def apply(plan: LogicalPlan): LogicalPlan = plan resolveOperators { + case u@UnresolvedRelation(nameParts, _, _) + if catalogManager.v1SessionCatalog.isTempView(Seq(nameParts.asIdentifier.name())) => + u + + case u@UnresolvedRelation(parts@CatalogAndIdentifier(catalog, ident), _, _) => + loadView(catalog, ident) + .map(createViewRelation(parts.quoted, _)) + .getOrElse(u) + + case p@SubqueryAlias(ident, view: IcebergView) if !p.child.resolved => + p.copy(child = qualifyTableIdentifiers(p.child, ident.qualifier)) + + case p@SubqueryAlias(_, view: IcebergView) => + p.copy(child = view) + } + + def loadView(catalog: CatalogPlugin, ident: Identifier): Option[View] = catalog match { + case viewCatalog: ViewCatalog => + try { + Option(viewCatalog.loadView(ident)) + } catch { + case _: NoSuchViewException => None + } + case _ => None + } + + private def createViewRelation(name: String, view: V2View): LogicalPlan = { + val child = parseViewText(name, view.query) Review Comment: Where would this fail in the analysis if the parsed view text was for some reason an "INSERT" or any other operation that couldn't be in a view? ########## spark/v3.5/spark-extensions/src/test/java/org/apache/iceberg/spark/extensions/TestViews.java: ########## @@ -0,0 +1,152 @@ +/* + * 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 static org.assertj.core.api.Assertions.assertThat; + +import java.util.List; +import java.util.Map; +import java.util.UUID; +import java.util.stream.Collectors; +import java.util.stream.IntStream; +import org.apache.iceberg.Schema; +import org.apache.iceberg.catalog.Catalog; +import org.apache.iceberg.catalog.Namespace; +import org.apache.iceberg.catalog.TableIdentifier; +import org.apache.iceberg.catalog.ViewCatalog; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.spark.Spark3Util; +import org.apache.iceberg.spark.SparkCatalogConfig; +import org.apache.iceberg.spark.source.SimpleRecord; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.catalyst.analysis.NoSuchTableException; +import org.junit.After; +import org.junit.Before; +import org.junit.Test; +import org.junit.runners.Parameterized; + +public class TestViews extends SparkExtensionsTestBase { Review Comment: Yeah and a stale view test https://github.com/apache/iceberg/pull/9332#discussion_r1430883652 -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
