[spark] branch branch-3.2 updated: [SPARK-36381][SQL] Add case sensitive and case insensitive compare for checking column name exist when alter table

[gu...@apache.org]

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

gurwls223 pushed a commit to branch branch-3.2
in repository https://gitbox.apache.org/repos/asf/spark.git


The following commit(s) were added to refs/heads/branch-3.2 by this push:
     new 8c42232  [SPARK-36381][SQL] Add case sensitive and case insensitive compare for checking column name exist when alter table
8c42232 is described below

commit 8c42232638e83215171492eab819b80165c04a5b
Author: PengLei <pe...@gmail.com>
AuthorDate: Wed Aug 4 10:04:13 2021 +0900

    [SPARK-36381][SQL] Add case sensitive and case insensitive compare for checking column name exist when alter table
    
    ### What changes were proposed in this pull request?
    Add the Resolver to `checkColumnNotExists` to check name exist in case sensitive.
    
    ### Why are the changes needed?
    At now the resolver is `_ == _` of `findNestedField`  called by `checkColumnNotExists`
    Add `alter.conf.resolver` to it.
    [SPARK-36381](https://issues.apache.org/jira/browse/SPARK-36381)
    ### Does this PR introduce _any_ user-facing change?
    No
    
    ### How was this patch tested?
    Add ut tests
    
    Closes #33618 from Peng-Lei/sensitive-cloumn-name.
    
    Authored-by: PengLei <pe...@gmail.com>
    Signed-off-by: Hyukjin Kwon <gu...@apache.org>
    (cherry picked from commit 87d49cbcb1b9003763148dec6a3b067cf86f6ab3)
    Signed-off-by: Hyukjin Kwon <gu...@apache.org>
---
 .../sql/catalyst/analysis/CheckAnalysis.scala      |  9 +++++----
 .../connector/V2CommandsCaseSensitivitySuite.scala | 22 ++++++++++++++++++++++
 2 files changed, 27 insertions(+), 4 deletions(-)

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
index 09cd71b..043bf95 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala
@@ -940,8 +940,9 @@ trait CheckAnalysis extends PredicateHelper with LookupCatalog {
    * Validates the options used for alter table commands after table and columns are resolved.
    */
   private def checkAlterTableCommand(alter: AlterTableCommand): Unit = {
-    def checkColumnNotExists(op: String, fieldNames: Seq[String], struct: StructType): Unit = {
-      if (struct.findNestedField(fieldNames, includeCollections = true).isDefined) {
+    def checkColumnNotExists(
+      op: String, fieldNames: Seq[String], struct: StructType, r: Resolver): Unit = {
+      if (struct.findNestedField(fieldNames, includeCollections = true, r).isDefined) {
         alter.failAnalysis(s"Cannot $op column, because ${fieldNames.quoted} " +
           s"already exists in ${struct.treeString}")
       }
@@ -950,7 +951,7 @@ trait CheckAnalysis extends PredicateHelper with LookupCatalog {
     alter match {
       case AddColumns(table: ResolvedTable, colsToAdd) =>
         colsToAdd.foreach { colToAdd =>
-          checkColumnNotExists("add", colToAdd.name, table.schema)
+          checkColumnNotExists("add", colToAdd.name, table.schema, alter.conf.resolver)
         }
         SchemaUtils.checkColumnNameDuplication(
           colsToAdd.map(_.name.quoted),
@@ -958,7 +959,7 @@ trait CheckAnalysis extends PredicateHelper with LookupCatalog {
           alter.conf.resolver)
 
       case RenameColumn(table: ResolvedTable, col: ResolvedFieldName, newName) =>
-        checkColumnNotExists("rename", col.path :+ newName, table.schema)
+        checkColumnNotExists("rename", col.path :+ newName, table.schema, alter.conf.resolver)
 
       case a @ AlterColumn(table: ResolvedTable, col: ResolvedFieldName, _, _, _, _) =>
         val fieldName = col.name.quoted
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/connector/V2CommandsCaseSensitivitySuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/connector/V2CommandsCaseSensitivitySuite.scala
index 1d6e0a8..0cc8d05 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/connector/V2CommandsCaseSensitivitySuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/connector/V2CommandsCaseSensitivitySuite.scala
@@ -249,6 +249,28 @@ class V2CommandsCaseSensitivitySuite extends SharedSparkSession with AnalysisTes
       expectErrorOnCaseSensitive = false)
   }
 
+  test("SPARK-36381: Check column name exist case sensitive and insensitive when add column") {
+    alterTableTest(
+      AddColumns(
+        table,
+        Seq(QualifiedColType(
+          None,
+          "ID",
+          LongType,
+          true,
+          None,
+          Some(UnresolvedFieldPosition(ColumnPosition.after("id")))))),
+      Seq("Cannot add column, because ID already exists in root"),
+      expectErrorOnCaseSensitive = false)
+  }
+
+  test("SPARK-36381: Check column name exist case sensitive and insensitive when rename column") {
+    alterTableTest(
+      RenameColumn(table, UnresolvedFieldName(Array("id")), "DATA"),
+      Seq("Cannot rename column, because DATA already exists in root"),
+      expectErrorOnCaseSensitive = false)
+  }
+
   test("AlterTable: drop column resolution") {
     Seq(Array("ID"), Array("point", "X"), Array("POINT", "X"), Array("POINT", "x")).foreach { ref =>
       alterTableTest(

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