[SPARK-29219][SQL] Introduce SupportsCatalogOptions for TableProvider #26913
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,53 @@ | ||
| /* | ||
| * 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.connector.catalog; | ||
|
|
||
| import org.apache.spark.annotation.Evolving; | ||
| import org.apache.spark.sql.util.CaseInsensitiveStringMap; | ||
|
|
||
| /** | ||
| * An interface, which TableProviders can implement, to support table existence checks and creation | ||
| * through a catalog, without having to use table identifiers. For example, when file based data | ||
| * sources use the `DataFrameWriter.save(path)` method, the option `path` can translate to a | ||
| * PathIdentifier. A catalog can then use this PathIdentifier to check the existence of a table, or | ||
| * whether a table can be created at a given directory. | ||
| */ | ||
| @Evolving | ||
| public interface SupportsCatalogOptions extends TableProvider { | ||
| /** | ||
| * Return a {@link Identifier} instance that can identify a table for a DataSource given | ||
| * DataFrame[Reader|Writer] options. | ||
| * | ||
| * @param options the user-specified options that can identify a table, e.g. file path, Kafka | ||
| * topic name, etc. It's an immutable case-insensitive string-to-string map. | ||
| */ | ||
| Identifier extractIdentifier(CaseInsensitiveStringMap options); | ||
|
|
||
| /** | ||
| * Return the name of a catalog that can be used to check the existence of, load, and create | ||
| * a table for this DataSource given the identifier that will be extracted by | ||
| * {@link #extractIdentifier(CaseInsensitiveStringMap) extractIdentifier}. A `null` value can | ||
| * be used to defer to the V2SessionCatalog. | ||
| * | ||
| * @param options the user-specified options that can identify a table, e.g. file path, Kafka | ||
| * topic name, etc. It's an immutable case-insensitive string-to-string map. | ||
| */ | ||
| default String extractCatalog(CaseInsensitiveStringMap options) { | ||
| return null; | ||
| } | ||
| } | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,145 @@ | ||
| /* | ||
| * 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.connector | ||
|
|
||
| import scala.language.implicitConversions | ||
|
|
||
| import org.scalatest.BeforeAndAfter | ||
|
|
||
| import org.apache.spark.sql.{QueryTest, SaveMode} | ||
| import org.apache.spark.sql.catalyst.analysis.TableAlreadyExistsException | ||
| import org.apache.spark.sql.connector.catalog.{Identifier, SupportsCatalogOptions, TableCatalog} | ||
| import org.apache.spark.sql.connector.catalog.CatalogManager.SESSION_CATALOG_NAME | ||
| import org.apache.spark.sql.internal.SQLConf.V2_SESSION_CATALOG_IMPLEMENTATION | ||
| import org.apache.spark.sql.test.SharedSparkSession | ||
| import org.apache.spark.sql.types.{LongType, StructType} | ||
| import org.apache.spark.sql.util.CaseInsensitiveStringMap | ||
|
|
||
| class SupportsCatalogOptionsSuite extends QueryTest with SharedSparkSession with BeforeAndAfter { | ||
|
|
||
| import testImplicits._ | ||
|
|
||
| private val catalogName = "testcat" | ||
| private val format = classOf[CatalogSupportingInMemoryTableProvider].getName | ||
|
|
||
| private def catalog(name: String): InMemoryTableSessionCatalog = { | ||
| spark.sessionState.catalogManager.catalog(name).asInstanceOf[InMemoryTableSessionCatalog] | ||
| } | ||
|
|
||
| private implicit def stringToIdentifier(value: String): Identifier = { | ||
| Identifier.of(Array.empty, value) | ||
| } | ||
|
|
||
| before { | ||
| spark.conf.set( | ||
| V2_SESSION_CATALOG_IMPLEMENTATION.key, classOf[InMemoryTableSessionCatalog].getName) | ||
| spark.conf.set( | ||
| s"spark.sql.catalog.$catalogName", classOf[InMemoryTableSessionCatalog].getName) | ||
| } | ||
|
|
||
| override def afterEach(): Unit = { | ||
| super.afterEach() | ||
| catalog(SESSION_CATALOG_NAME).clearTables() | ||
| catalog(catalogName).clearTables() | ||
| spark.conf.unset(V2_SESSION_CATALOG_IMPLEMENTATION.key) | ||
| spark.conf.unset(s"spark.sql.catalog.$catalogName") | ||
| } | ||
|
|
||
| def testWithDifferentCatalogs(withCatalogOption: Option[String]): Unit = { | ||
| Seq(SaveMode.ErrorIfExists, SaveMode.Ignore).foreach { saveMode => | ||
| test(s"save works with $saveMode - no table, no partitioning, session catalog, " + | ||
rdblue marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| s"withCatalog: ${withCatalogOption.isDefined}") { | ||
| val df = spark.range(10) | ||
| val dfw = df.write.format(format).mode(saveMode).option("name", "t1") | ||
| withCatalogOption.foreach(cName => dfw.option("catalog", cName)) | ||
| dfw.save() | ||
|
|
||
| val table = catalog(withCatalogOption.getOrElse(SESSION_CATALOG_NAME)).loadTable("t1") | ||
| assert(table.name() === "t1", "Table identifier was wrong") | ||
| assert(table.partitioning().isEmpty, "Partitioning should be empty") | ||
| assert(table.schema() === df.schema.asNullable, "Schema did not match") | ||
|
|
||
| val dfr = spark.read.format(format).option("name", "t1") | ||
| withCatalogOption.foreach(cName => dfr.option("catalog", cName)) | ||
| checkAnswer(dfr.load(), df.toDF()) | ||
| } | ||
|
|
||
| test(s"save works with $saveMode - no table, with partitioning, session catalog, " + | ||
| s"withCatalog: ${withCatalogOption.isDefined}") { | ||
| val df = spark.range(10).withColumn("part", 'id % 5) | ||
| val dfw = df.write.format(format).mode(saveMode).option("name", "t1").partitionBy("part") | ||
| withCatalogOption.foreach(cName => dfw.option("catalog", cName)) | ||
| dfw.save() | ||
|
|
||
| val table = catalog(withCatalogOption.getOrElse(SESSION_CATALOG_NAME)).loadTable("t1") | ||
| assert(table.name() === "t1", "Table identifier was wrong") | ||
| assert(table.partitioning().length === 1, "Partitioning should not be empty") | ||
| assert(table.partitioning().head.references().head.fieldNames().head === "part", | ||
| "Partitioning was incorrect") | ||
| assert(table.schema() === df.schema.asNullable, "Schema did not match") | ||
|
|
||
| val dfr = spark.read.format(format).option("name", "t1") | ||
| withCatalogOption.foreach(cName => dfr.option("catalog", cName)) | ||
| checkAnswer(dfr.load(), df.toDF()) | ||
| } | ||
| } | ||
|
|
||
| test(s"save fails with ErrorIfExists if table exists, withCatalog: ${withCatalogOption.isDefined}") { | ||
| sql("create table t1 (id bigint) using foo") | ||
| val df = spark.range(10) | ||
| intercept[TableAlreadyExistsException] { | ||
| val dfw = df.write.format(format).option("name", "t1") | ||
| withCatalogOption.foreach(cName => dfw.option("catalog", cName)) | ||
| dfw.save() | ||
| } | ||
| } | ||
|
|
||
| test(s"Ignore mode if table exists, withCatalog: ${withCatalogOption.isDefined}") { | ||
| sql("create table t1 (id bigint) using foo") | ||
| val df = spark.range(10).withColumn("part", 'id % 5) | ||
| intercept[TableAlreadyExistsException] { | ||
| val dfw = df.write.format(format).mode(SaveMode.Ignore).option("name", "t1") | ||
| withCatalogOption.foreach(cName => dfw.option("catalog", cName)) | ||
| dfw.save() | ||
| } | ||
|
|
||
| val table = catalog(SESSION_CATALOG_NAME).loadTable("t1") | ||
| assert(table.partitioning().isEmpty, "Partitioning should be empty") | ||
| assert(table.schema() === new StructType().add("id", LongType), "Schema did not match") | ||
| } | ||
| } | ||
|
|
||
| testWithDifferentCatalogs(None) | ||
|
|
||
| testWithDifferentCatalogs(Some(catalogName)) | ||
| } | ||
|
|
||
| class CatalogSupportingInMemoryTableProvider | ||
| extends InMemoryTableProvider | ||
| with SupportsCatalogOptions { | ||
|
|
||
| override def extractIdentifier(options: CaseInsensitiveStringMap): Identifier = { | ||
| val name = options.get("name") | ||
| assert(name != null, "The name should be provided for this table") | ||
| Identifier.of(Array.empty, name) | ||
| } | ||
|
|
||
| override def extractCatalog(options: CaseInsensitiveStringMap): String = { | ||
| options.get("catalog") | ||
| } | ||
| } | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
shall we by default return
CatalogManager.SESSION_CATALOG_NAMEinstead of null?