[spark] branch branch-3.0 updated: [SPARK-30903][SQL] Fail fast on duplicate columns when analyze columns

[ya...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

yamamuro pushed a commit to branch branch-3.0
in repository https://gitbox.apache.org/repos/asf/spark.git


The following commit(s) were added to refs/heads/branch-3.0 by this push:
     new 4a82ead  [SPARK-30903][SQL] Fail fast on duplicate columns when analyze columns
4a82ead is described below

commit 4a82ead147c944c8d4828bbbd4a7e3ec3d3e1135
Author: yi.wu <yi...@databricks.com>
AuthorDate: Sun Feb 23 09:52:54 2020 +0900

    [SPARK-30903][SQL] Fail fast on duplicate columns when analyze columns
    
    <!--
    Thanks for sending a pull request!  Here are some tips for you:
      1. If this is your first time, please read our contributor guidelines: https://spark.apache.org/contributing.html
      2. Ensure you have added or run the appropriate tests for your PR: https://spark.apache.org/developer-tools.html
      3. If the PR is unfinished, add '[WIP]' in your PR title, e.g., '[WIP][SPARK-XXXX] Your PR title ...'.
      4. Be sure to keep the PR description updated to reflect all changes.
      5. Please write your PR title to summarize what this PR proposes.
      6. If possible, provide a concise example to reproduce the issue for a faster review.
      7. If you want to add a new configuration, please read the guideline first for naming configurations in
         'core/src/main/scala/org/apache/spark/internal/config/ConfigEntry.scala'.
    -->
    
    ### What changes were proposed in this pull request?
    <!--
    Please clarify what changes you are proposing. The purpose of this section is to outline the changes and how this PR fixes the issue.
    If possible, please consider writing useful notes for better and faster reviews in your PR. See the examples below.
      1. If you refactor some codes with changing classes, showing the class hierarchy will help reviewers.
      2. If you fix some SQL features, you can provide some references of other DBMSes.
      3. If there is design documentation, please add the link.
      4. If there is a discussion in the mailing list, please add the link.
    -->
    
    Add new `CommandCheck` rule and fail fast when detects duplicate columns in `AnalyzeColumnCommand`.
    
    ### Why are the changes needed?
    <!--
    Please clarify why the changes are needed. For instance,
      1. If you propose a new API, clarify the use case for a new API.
      2. If you fix a bug, you can clarify why it is a bug.
    -->
    
    To avoid duplicate statistics computation for the same column in `AnalyzeColumnCommand`.
    
    ### Does this PR introduce any user-facing change?
    <!--
    If yes, please clarify the previous behavior and the change this PR proposes - provide the console output, description and/or an example to show the behavior difference if possible.
    If no, write 'No'.
    -->
    
    Yes. User now get exception when input duplicate columns.
    
    ### How was this patch tested?
    <!--
    If tests were added, say they were added here. Please make sure to add some test cases that check the changes thoroughly including negative and positive cases if possible.
    If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future.
    If tests were not added, please describe why they were not added and/or why it was difficult to add.
    -->
    
    Added new test.
    
    Closes #27651 from Ngone51/fail_on_dup_cols.
    
    Authored-by: yi.wu <yi...@databricks.com>
    Signed-off-by: Takeshi Yamamuro <ya...@apache.org>
    (cherry picked from commit 25f5bfaa6e624da7f491e770a2383038fc6009e1)
    Signed-off-by: Takeshi Yamamuro <ya...@apache.org>
---
 .../spark/sql/execution/command/CommandCheck.scala | 38 ++++++++++++++++++++++
 .../sql/internal/BaseSessionStateBuilder.scala     |  2 ++
 .../spark/sql/StatisticsCollectionSuite.scala      | 17 ++++++++++
 .../spark/sql/hive/HiveSessionStateBuilder.scala   |  2 ++
 4 files changed, 59 insertions(+)

diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/command/CommandCheck.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/command/CommandCheck.scala
new file mode 100644
index 0000000..dedace4
--- /dev/null
+++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/command/CommandCheck.scala
@@ -0,0 +1,38 @@
+/*
+ * 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.catalyst.plans.logical.LogicalPlan
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.util.SchemaUtils
+
+/**
+ * Checks legitimization of various execution commands.
+ */
+case class CommandCheck(conf: SQLConf) extends (LogicalPlan => Unit) {
+
+  override def apply(plan: LogicalPlan): Unit = {
+    plan.foreach {
+      case AnalyzeColumnCommand(_, colsOpt, allColumns) if !allColumns =>
+        colsOpt.foreach(SchemaUtils.checkColumnNameDuplication(
+          _, "in analyze columns.", conf.caseSensitiveAnalysis))
+
+      case _ =>
+    }
+  }
+}
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala b/sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala
index 2137fe2..20e1b56 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/internal/BaseSessionStateBuilder.scala
@@ -28,6 +28,7 @@ import org.apache.spark.sql.catalyst.rules.Rule
 import org.apache.spark.sql.connector.catalog.CatalogManager
 import org.apache.spark.sql.execution.{ColumnarRule, QueryExecution, SparkOptimizer, SparkPlanner, SparkSqlParser}
 import org.apache.spark.sql.execution.analysis.DetectAmbiguousSelfJoin
+import org.apache.spark.sql.execution.command.CommandCheck
 import org.apache.spark.sql.execution.datasources._
 import org.apache.spark.sql.execution.datasources.v2.{TableCapabilityCheck, V2SessionCatalog}
 import org.apache.spark.sql.streaming.StreamingQueryManager
@@ -190,6 +191,7 @@ abstract class BaseSessionStateBuilder(
         PreReadCheck +:
         HiveOnlyCheck +:
         TableCapabilityCheck +:
+        CommandCheck(conf) +:
         customCheckRules
   }
 
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/StatisticsCollectionSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/StatisticsCollectionSuite.scala
index e9ceab6..30b15a8 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/StatisticsCollectionSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/StatisticsCollectionSuite.scala
@@ -650,4 +650,21 @@ class StatisticsCollectionSuite extends StatisticsCollectionTestBase with Shared
       }
     }
   }
+
+  Seq(true, false).foreach { caseSensitive =>
+    test(s"SPARK-30903: Fail fast on duplicate columns when analyze columns " +
+      s"- caseSensitive=$caseSensitive") {
+      withSQLConf(SQLConf.CASE_SENSITIVE.key -> caseSensitive.toString) {
+        val table = "test_table"
+        withTable(table) {
+          sql(s"CREATE TABLE $table (value string, name string) USING PARQUET")
+          val dupCol = if (caseSensitive) "value" else "VaLuE"
+          val errorMsg = intercept[AnalysisException] {
+            sql(s"ANALYZE TABLE $table COMPUTE STATISTICS FOR COLUMNS value, name, $dupCol")
+          }.getMessage
+          assert(errorMsg.contains("Found duplicate column(s)"))
+        }
+      }
+    }
+  }
 }
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveSessionStateBuilder.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveSessionStateBuilder.scala
index 1858fbd..7ec52ba 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveSessionStateBuilder.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveSessionStateBuilder.scala
@@ -26,6 +26,7 @@ import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
 import org.apache.spark.sql.catalyst.rules.Rule
 import org.apache.spark.sql.execution.{SparkOptimizer, SparkPlanner}
 import org.apache.spark.sql.execution.analysis.DetectAmbiguousSelfJoin
+import org.apache.spark.sql.execution.command.CommandCheck
 import org.apache.spark.sql.execution.datasources._
 import org.apache.spark.sql.execution.datasources.v2.TableCapabilityCheck
 import org.apache.spark.sql.hive.client.HiveClient
@@ -93,6 +94,7 @@ class HiveSessionStateBuilder(session: SparkSession, parentState: Option[Session
       PreWriteCheck +:
         PreReadCheck +:
         TableCapabilityCheck +:
+        CommandCheck(conf) +:
         customCheckRules
   }
 


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org