You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by hv...@apache.org on 2023/02/27 13:11:56 UTC
[spark] branch master updated: [SPARK-42581][CONNECT] Add SQLImplicits
This is an automated email from the ASF dual-hosted git repository.
hvanhovell pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new f0aef011e35 [SPARK-42581][CONNECT] Add SQLImplicits
f0aef011e35 is described below
commit f0aef011e35a4f561764fdc1da9f32658cc14977
Author: Herman van Hovell <he...@databricks.com>
AuthorDate: Mon Feb 27 09:11:40 2023 -0400
[SPARK-42581][CONNECT] Add SQLImplicits
### What changes were proposed in this pull request?
This PR adds the `SQLImplicits` class to Spark Connect. This makes it easier for end users to work with Connect Datasets.
The current implementation only contains the column conversions, we will add the encoder implicits in a follow-up.
### Why are the changes needed?
API Parity.
### Does this PR introduce _any_ user-facing change?
Yes.
### How was this patch tested?
I added a new test suite: `SQLImplicitTestSuite.`
Closes #40186 from hvanhovell/SPARK-42581.
Authored-by: Herman van Hovell <he...@databricks.com>
Signed-off-by: Herman van Hovell <he...@databricks.com>
---
.../scala/org/apache/spark/sql/SQLImplicits.scala | 44 ++++++++++++++++++++
.../scala/org/apache/spark/sql/SparkSession.scala | 16 ++++++++
.../apache/spark/sql/SQLImplicitsTestSuite.scala | 47 ++++++++++++++++++++++
.../sql/connect/client/CompatibilitySuite.scala | 1 -
4 files changed, 107 insertions(+), 1 deletion(-)
diff --git a/connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/SQLImplicits.scala b/connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/SQLImplicits.scala
new file mode 100644
index 00000000000..e63c9481da5
--- /dev/null
+++ b/connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/SQLImplicits.scala
@@ -0,0 +1,44 @@
+/*
+ * 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
+
+import scala.language.implicitConversions
+
+/**
+ * A collection of implicit methods for converting names and Symbols into [[Column]]s.
+ *
+ * @since 3.4.0
+ */
+abstract class SQLImplicits {
+
+ /**
+ * Converts $"col name" into a [[Column]].
+ *
+ * @since 3.4.0
+ */
+ implicit class StringToColumn(val sc: StringContext) {
+ def $(args: Any*): ColumnName = {
+ new ColumnName(sc.s(args: _*))
+ }
+ }
+
+ /**
+ * An implicit conversion that turns a Scala `Symbol` into a [[Column]].
+ * @since 3.4.0
+ */
+ implicit def symbolToColumn(s: Symbol): ColumnName = new ColumnName(s.name)
+}
diff --git a/connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/SparkSession.scala b/connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/SparkSession.scala
index b1b1f4b0a4e..e85c7008ca9 100644
--- a/connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/SparkSession.scala
+++ b/connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/SparkSession.scala
@@ -201,6 +201,22 @@ class SparkSession(
range(start, end, step, Option(numPartitions))
}
+ // scalastyle:off
+ // Disable style checker so "implicits" object can start with lowercase i
+ /**
+ * (Scala-specific) Implicit methods available in Scala for converting common names and
+ * [[Symbol]]s into [[Column]]s.
+ *
+ * {{{
+ * val sparkSession = SparkSession.builder.getOrCreate()
+ * import sparkSession.implicits._
+ * }}}
+ *
+ * @since 3.4.0
+ */
+ object implicits extends SQLImplicits
+ // scalastyle:on
+
private def range(
start: Long,
end: Long,
diff --git a/connector/connect/client/jvm/src/test/scala/org/apache/spark/sql/SQLImplicitsTestSuite.scala b/connector/connect/client/jvm/src/test/scala/org/apache/spark/sql/SQLImplicitsTestSuite.scala
new file mode 100644
index 00000000000..1f141d7c71a
--- /dev/null
+++ b/connector/connect/client/jvm/src/test/scala/org/apache/spark/sql/SQLImplicitsTestSuite.scala
@@ -0,0 +1,47 @@
+/*
+ * 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
+
+import java.util.concurrent.atomic.AtomicLong
+
+import io.grpc.inprocess.InProcessChannelBuilder
+import org.scalatest.BeforeAndAfterAll
+
+import org.apache.spark.connect.proto
+import org.apache.spark.sql.connect.client.SparkConnectClient
+import org.apache.spark.sql.connect.client.util.ConnectFunSuite
+
+class SQLImplicitsTestSuite extends ConnectFunSuite with BeforeAndAfterAll {
+ private var session: SparkSession = _
+
+ override protected def beforeAll(): Unit = {
+ super.beforeAll()
+ val client = SparkConnectClient(
+ proto.UserContext.newBuilder().build(),
+ InProcessChannelBuilder.forName("/dev/null").build())
+ session =
+ new SparkSession(client, cleaner = SparkSession.cleaner, planIdGenerator = new AtomicLong)
+ }
+
+ test("column resolution") {
+ val spark = session
+ import spark.implicits._
+ def assertEqual(left: Column, right: Column): Unit = assert(left == right)
+ assertEqual($"x", Column("x"))
+ assertEqual('y, Column("y"))
+ }
+}
diff --git a/connector/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/client/CompatibilitySuite.scala b/connector/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/client/CompatibilitySuite.scala
index 5546542898e..bb480e0ee08 100644
--- a/connector/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/client/CompatibilitySuite.scala
+++ b/connector/connect/client/jvm/src/test/scala/org/apache/spark/sql/connect/client/CompatibilitySuite.scala
@@ -152,7 +152,6 @@ class CompatibilitySuite extends ConnectFunSuite {
ProblemFilters.exclude[Problem]("org.apache.spark.sql.SparkSession.getActiveSession"),
ProblemFilters.exclude[Problem]("org.apache.spark.sql.SparkSession.clearDefaultSession"),
ProblemFilters.exclude[Problem]("org.apache.spark.sql.SparkSession.setDefaultSession"),
- ProblemFilters.exclude[Problem]("org.apache.spark.sql.SparkSession.implicits"),
ProblemFilters.exclude[Problem]("org.apache.spark.sql.SparkSession.sparkContext"),
ProblemFilters.exclude[Problem]("org.apache.spark.sql.SparkSession.sharedState"),
ProblemFilters.exclude[Problem]("org.apache.spark.sql.SparkSession.sessionState"),
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org