Github user mbasmanova commented on a diff in the pull request:

    https://github.com/apache/spark/pull/18421#discussion_r131957033
  
    --- Diff: 
sql/core/src/main/scala/org/apache/spark/sql/execution/command/AnalyzePartitionCommand.scala
 ---
    @@ -0,0 +1,138 @@
    +/*
    + * 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.command
    +
    +import org.apache.spark.sql.{AnalysisException, Column, Row, SparkSession}
    +import org.apache.spark.sql.catalyst.TableIdentifier
    +import org.apache.spark.sql.catalyst.analysis.{NoSuchPartitionException, 
UnresolvedAttribute}
    +import org.apache.spark.sql.catalyst.catalog.{CatalogTable, 
CatalogTableType}
    +import 
org.apache.spark.sql.catalyst.catalog.CatalogTypes.TablePartitionSpec
    +import org.apache.spark.sql.catalyst.expressions.{And, EqualTo, Literal}
    +
    +/**
    + * Analyzes a given set of partitions to generate per-partition 
statistics, which will be used in
    + * query optimizations.
    + *
    + * When `partitionSpec` is empty, statistics for all partitions are 
collected and stored in
    + * Metastore.
    + *
    + * When `partitionSpec` mentions only some of the partition columns, all 
partitions with
    + * matching values for specified columns are processed.
    + *
    + * If `partitionSpec` mentions unknown partition column, an 
`AnalysisException` is raised.
    + *
    + * By default, total number of rows and total size in bytes is calculated. 
When `noscan`
    + * is `false`, only total size in bytes is computed.
    + */
    +case class AnalyzePartitionCommand(
    +    tableIdent: TableIdentifier,
    +    partitionSpec: Map[String, Option[String]],
    +    noscan: Boolean = true) extends RunnableCommand {
    +
    +  private def validatePartitionSpec(table: CatalogTable): 
Option[TablePartitionSpec] = {
    +    val partitionColumnNames = table.partitionColumnNames.toSet
    +    val invalidColumnNames = 
partitionSpec.keys.filterNot(partitionColumnNames.contains(_))
    +    if (invalidColumnNames.nonEmpty) {
    +      val tableId = table.identifier
    +      throw new AnalysisException(s"Partition specification for table 
'${tableId.table}' " +
    +        s"in database '${tableId.database.get}' refers to unknown 
partition column(s): " +
    +        invalidColumnNames.mkString(","))
    +    }
    +
    +    val filteredSpec = partitionSpec.filter(_._2.isDefined)
    --- End diff --
    
    @gatorsmile , this PR doesn't impose this requirement. Hive docs also 
doesn't list it: https://cwiki.apache.org/confluence/display/Hive/StatsDev


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to