[GitHub] [hudi] XuQianJin-Stars commented on a change in pull request #4901: [HUDI-3445] Support Clustering Command Based on Call Procedure Command for Spark SQL

[GitBox <gi...@apache.org>]

XuQianJin-Stars commented on a change in pull request #4901:
URL: https://github.com/apache/hudi/pull/4901#discussion_r818639313



##########
File path: hudi-client/hudi-client-common/src/main/java/org/apache/hudi/table/action/cluster/strategy/PartitionAwareClusteringPlanStrategy.java
##########
@@ -113,6 +114,15 @@ public PartitionAwareClusteringPlanStrategy(HoodieTable table, HoodieEngineConte
         .build());
   }
 
+  public List<String> getMatchedPartitions(HoodieWriteConfig config, List<String> partitionPaths) {
+    String partitionSelected = config.getClusteringPartitionSelected();
+    if (!StringUtils.isNullOrEmpty(partitionSelected)) {
+      return Arrays.asList(partitionSelected.split(","));

Review comment:
       `delimiter`which is comma by default?

##########
File path: hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/command/procedures/BaseProcedure.scala
##########
@@ -96,4 +110,40 @@ abstract class BaseProcedure extends Procedure {
         throw new UnsupportedOperationException(s"type: ${dataType.typeName} not supported")
     }
   }
+
+  protected def getBasePath(tableName: Option[Any], tablePath: Option[Any]): String = {
+    tableName.map(
+      t => HoodieCatalogTable(sparkSession, new TableIdentifier(t.asInstanceOf[String])).tableLocation)
+      .getOrElse(
+        tablePath.map(p => p.asInstanceOf[String]).getOrElse(
+          throw new HoodieClusteringException("Table name or table path must be given one"))
+      )
+  }
+
+  protected def convertCatalystType(value: String, dataType: DataType): Any = {
+    try {
+      val valueWithType = dataType match {
+        case StringType => value
+        case BinaryType => value.getBytes(Charset.forName("utf-8"))
+        case BooleanType => value.toBoolean
+        case DoubleType => value.toDouble
+        case _: DecimalType => Decimal(BigDecimal(value))

Review comment:
       Does the `precision` of decimal need not be processed?

##########
File path: hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/command/procedures/ShowClusteringProcedure.scala
##########
@@ -0,0 +1,69 @@
+/*
+ * 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.hudi.command.procedures
+
+import org.apache.hudi.SparkAdapterSupport
+import org.apache.hudi.common.table.HoodieTableMetaClient
+import org.apache.hudi.common.util.ClusteringUtils
+import org.apache.spark.internal.Logging
+import org.apache.spark.sql.Row
+import org.apache.spark.sql.types._
+
+import java.util.function.Supplier
+import scala.collection.JavaConverters._
+
+class ShowClusteringProcedure extends BaseProcedure with ProcedureBuilder with SparkAdapterSupport with Logging {
+  private val PARAMETERS = Array[ProcedureParameter](
+    ProcedureParameter.optional(0, "table", DataTypes.StringType, None),

Review comment:
       ditto table 

##########
File path: hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/command/procedures/RunClusteringProcedure.scala
##########
@@ -0,0 +1,176 @@
+/*
+ * 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.hudi.command.procedures
+
+import org.apache.hudi.BaseHoodieTableFileIndex.PartitionPath
+import org.apache.hudi.client.common.HoodieSparkEngineContext
+import org.apache.hudi.common.config.HoodieMetadataConfig
+import org.apache.hudi.common.table.timeline.HoodieActiveTimeline
+import org.apache.hudi.common.table.view.FileSystemViewStorageConfig
+import org.apache.hudi.common.table.{HoodieTableMetaClient, TableSchemaResolver}
+import org.apache.hudi.common.util.{ClusteringUtils, Option => HOption}
+import org.apache.hudi.config.HoodieClusteringConfig
+import org.apache.hudi.exception.HoodieClusteringException
+import org.apache.hudi.metadata.HoodieTableMetadata
+import org.apache.hudi.{HoodieCommonUtils, SparkAdapterSupport}
+import org.apache.spark.api.java.JavaSparkContext
+import org.apache.spark.internal.Logging
+import org.apache.spark.sql.Row
+import org.apache.spark.sql.catalyst.expressions.Expression
+import org.apache.spark.sql.types._
+
+import java.util.Properties
+import java.util.function.Supplier
+import scala.collection.JavaConverters
+import scala.collection.JavaConverters._
+
+class RunClusteringProcedure extends BaseProcedure with ProcedureBuilder with SparkAdapterSupport with Logging {
+  /**
+   * OPTIMIZE table_name|table_path [WHERE predicate]
+   * [ORDER BY (col_name1 [, ...] ) ]
+   */
+  private val PARAMETERS = Array[ProcedureParameter](
+    ProcedureParameter.optional(0, "table", DataTypes.StringType, None),

Review comment:
       table is also optional，not required？




-- 
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: commits-unsubscribe@hudi.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org