1
0

[HUDI-1869] Upgrading Spark3 To 3.1 (#3844)

Co-authored-by: pengzhiwei <pengzhiwei2015@icloud.com>
This commit is contained in:
Yann Byron
2021-11-03 09:25:12 +08:00
committed by GitHub
parent dee3a14aae
commit 1f17467f73
22 changed files with 315 additions and 57 deletions

View File

@@ -0,0 +1,46 @@
/*
* 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.hudi.spark3.internal;
import org.apache.spark.sql.catalyst.plans.logical.InsertIntoStatement;
import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan;
import scala.Option;
import scala.collection.Seq;
import scala.collection.immutable.Map;
import java.lang.reflect.Constructor;
public class ReflectUtil {
public static InsertIntoStatement createInsertInto(boolean isSpark30, LogicalPlan table, Map<String, Option<String>> partition, Seq<String> userSpecifiedCols,
LogicalPlan query, boolean overwrite, boolean ifPartitionNotExists) {
try {
if (isSpark30) {
Constructor<InsertIntoStatement> constructor = InsertIntoStatement.class.getConstructor(
LogicalPlan.class, Map.class, LogicalPlan.class, boolean.class, boolean.class);
return constructor.newInstance(table, partition, query, overwrite, ifPartitionNotExists);
} else {
Constructor<InsertIntoStatement> constructor = InsertIntoStatement.class.getConstructor(
LogicalPlan.class, Map.class, Seq.class, LogicalPlan.class, boolean.class, boolean.class);
return constructor.newInstance(table, partition, userSpecifiedCols, query, overwrite, ifPartitionNotExists);
}
} catch (Exception e) {
throw new RuntimeException("Error in create InsertIntoStatement", e);
}
}
}

View File

@@ -19,10 +19,13 @@ package org.apache.spark.sql.adapter
import org.apache.hudi.Spark3RowSerDe
import org.apache.hudi.client.utils.SparkRowSerDe
import org.apache.hudi.spark3.internal.ReflectUtil
import org.apache.spark.SPARK_VERSION
import org.apache.spark.sql.Row
import org.apache.spark.sql.catalyst.analysis.UnresolvedRelation
import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder
import org.apache.spark.sql.catalyst.expressions.{Expression, Like}
import org.apache.spark.sql.catalyst.parser.ParserInterface
import org.apache.spark.sql.catalyst.plans.JoinType
import org.apache.spark.sql.catalyst.plans.logical.{InsertIntoStatement, Join, JoinHint, LogicalPlan}
import org.apache.spark.sql.catalyst.{AliasIdentifier, TableIdentifier}
@@ -67,15 +70,16 @@ class Spark3Adapter extends SparkAdapter {
override def getInsertIntoChildren(plan: LogicalPlan):
Option[(LogicalPlan, Map[String, Option[String]], LogicalPlan, Boolean, Boolean)] = {
plan match {
case InsertIntoStatement(table, partitionSpec, query, overwrite, ifPartitionNotExists) =>
Some((table, partitionSpec, query, overwrite, ifPartitionNotExists))
case _=> None
case insert: InsertIntoStatement =>
Some((insert.table, insert.partitionSpec, insert.query, insert.overwrite, insert.ifPartitionNotExists))
case _ =>
None
}
}
override def createInsertInto(table: LogicalPlan, partition: Map[String, Option[String]],
query: LogicalPlan, overwrite: Boolean, ifPartitionNotExists: Boolean): LogicalPlan = {
InsertIntoStatement(table, partition, query, overwrite, ifPartitionNotExists)
ReflectUtil.createInsertInto(SPARK_VERSION.startsWith("3.0"), table, partition, Seq.empty[String], query, overwrite, ifPartitionNotExists)
}
override def createSparkParsePartitionUtil(conf: SQLConf): SparkParsePartitionUtil = {
@@ -85,4 +89,8 @@ class Spark3Adapter extends SparkAdapter {
override def createLike(left: Expression, right: Expression): Expression = {
new Like(left, right)
}
override def parseMultipartIdentifier(parser: ParserInterface, sqlText: String): Seq[String] = {
parser.parseMultipartIdentifier(sqlText)
}
}