viirya commented on a change in pull request #29066:
URL: https://github.com/apache/spark/pull/29066#discussion_r467515565
##########
File path:
sql/catalyst/src/main/java/org/apache/spark/sql/connector/write/WriteBuilder.java
##########
@@ -23,17 +23,34 @@
import org.apache.spark.sql.connector.write.streaming.StreamingWrite;
/**
- * An interface for building the {@link BatchWrite}. Implementations can mix
in some interfaces to
+ * An interface for building the {@link Write}. Implementations can mix in
some interfaces to
* support different ways to write data to data sources.
*
- * Unless modified by a mixin interface, the {@link BatchWrite} configured by
this builder is to
+ * Unless modified by a mixin interface, the {@link Write} configured by this
builder is to
* append data without affecting existing data.
*
* @since 3.0.0
*/
@Evolving
public interface WriteBuilder {
+ /**
+ * Returns a logical {@link Write} shared between batch and streaming.
+ */
+ default Write build() {
Review comment:
This API looks like overlapping in function with `buildForBatch` and
`buildForStreaming`? Which one we should use? `build` then `toBatch`/`toStream`
or `buildForBatch`/`buildForStreaming`?
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2Writes.scala
##########
@@ -0,0 +1,102 @@
+/*
+ * 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 java.util.UUID
+
+import org.apache.spark.SparkException
+import org.apache.spark.sql.AnalysisException
+import org.apache.spark.sql.catalyst.expressions.PredicateHelper
+import org.apache.spark.sql.catalyst.plans.logical.{AppendData, Command,
LogicalPlan, OverwriteByExpression, OverwritePartitionsDynamic}
+import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.connector.catalog.Table
+import org.apache.spark.sql.connector.write.{LogicalWriteInfoImpl,
SupportsDynamicOverwrite, SupportsOverwrite, SupportsTruncate, Write,
WriteBuilder}
+import org.apache.spark.sql.execution.datasources.DataSourceStrategy
+import org.apache.spark.sql.sources.{AlwaysTrue, Filter}
+
+/**
+ * A rule that constructs [[Write]]s.
+ */
+object V2Writes extends Rule[LogicalPlan] with PredicateHelper {
+
+ import DataSourceV2Implicits._
+
+ override def apply(plan: LogicalPlan): LogicalPlan = plan transformDown {
+ case AppendData(relation: DataSourceV2Relation, query, options, _) =>
+ val writeBuilder = newWriteBuilder(relation.table, query, options)
+ val write = writeBuilder.build()
+ V2BatchWriteCommand(write, query)
+
+ case OverwriteByExpression(relation: DataSourceV2Relation, deleteExpr,
query, options, _) =>
+ // fail if any filter cannot be converted. correctness depends on
removing all matching data.
+ val filters = splitConjunctivePredicates(deleteExpr).map {
+ filter => DataSourceStrategy.translateFilter(deleteExpr,
+ supportNestedPredicatePushdown = true).getOrElse(
+ throw new AnalysisException(s"Cannot translate expression to source
filter: $filter"))
+ }.toArray
Review comment:
By the change, we move catalyst expression -> sources.Filter conversion
to logical plans. So we will see both catalyst expressions and
sources.expressions in logical plans in optimization.
Is it more clear if we use only catalyst expressions in logical plans, and
convert to sources.Filter in physical plans when we need to interact
datasources?
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2Writes.scala
##########
@@ -0,0 +1,102 @@
+/*
+ * 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 java.util.UUID
+
+import org.apache.spark.SparkException
+import org.apache.spark.sql.AnalysisException
+import org.apache.spark.sql.catalyst.expressions.PredicateHelper
+import org.apache.spark.sql.catalyst.plans.logical.{AppendData, Command,
LogicalPlan, OverwriteByExpression, OverwritePartitionsDynamic}
+import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.connector.catalog.Table
+import org.apache.spark.sql.connector.write.{LogicalWriteInfoImpl,
SupportsDynamicOverwrite, SupportsOverwrite, SupportsTruncate, Write,
WriteBuilder}
+import org.apache.spark.sql.execution.datasources.DataSourceStrategy
+import org.apache.spark.sql.sources.{AlwaysTrue, Filter}
+
+/**
+ * A rule that constructs [[Write]]s.
+ */
+object V2Writes extends Rule[LogicalPlan] with PredicateHelper {
+
+ import DataSourceV2Implicits._
+
+ override def apply(plan: LogicalPlan): LogicalPlan = plan transformDown {
+ case AppendData(relation: DataSourceV2Relation, query, options, _) =>
+ val writeBuilder = newWriteBuilder(relation.table, query, options)
+ val write = writeBuilder.build()
+ V2BatchWriteCommand(write, query)
+
+ case OverwriteByExpression(relation: DataSourceV2Relation, deleteExpr,
query, options, _) =>
+ // fail if any filter cannot be converted. correctness depends on
removing all matching data.
+ val filters = splitConjunctivePredicates(deleteExpr).map {
+ filter => DataSourceStrategy.translateFilter(deleteExpr,
+ supportNestedPredicatePushdown = true).getOrElse(
+ throw new AnalysisException(s"Cannot translate expression to source
filter: $filter"))
+ }.toArray
Review comment:
And later in V2WriteRequirements, we also need to convert sources.Filter
back to catalyst expressions.
----------------------------------------------------------------
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]
