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

wenchen pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git


The following commit(s) were added to refs/heads/master by this push:
     new 6a17b794338b [SPARK-48305][SQL] Add collation support for CurrentLike 
expressions
6a17b794338b is described below

commit 6a17b794338b0473c11ae17e5c8f1450c0b3f358
Author: Uros Bojanic <157381213+uros...@users.noreply.github.com>
AuthorDate: Mon May 20 15:51:23 2024 +0800

    [SPARK-48305][SQL] Add collation support for CurrentLike expressions
    
    ### What changes were proposed in this pull request?
    Introduce collation awareness for CurrentLike expressions: 
current_database/current_schema, current_catalog, 
user/current_user/session_user.
    
    ### Why are the changes needed?
    Add collation support for CurrentLike expressions in Spark.
    
    ### Does this PR introduce _any_ user-facing change?
    Yes, users should now be able to use collated strings within arguments for 
CurrentLike functions: current_database/current_schema, current_catalog, 
user/current_user/session_user.
    
    ### How was this patch tested?
    E2e sql tests.
    
    ### Was this patch authored or co-authored using generative AI tooling?
    No.
    
    Closes #46613 from uros-db/current-like-expressions.
    
    Authored-by: Uros Bojanic <157381213+uros...@users.noreply.github.com>
    Signed-off-by: Wenchen Fan <wenc...@databricks.com>
---
 .../org/apache/spark/sql/catalyst/expressions/misc.scala |  6 +++---
 .../spark/sql/catalyst/optimizer/finishAnalysis.scala    |  7 ++++---
 .../apache/spark/sql/CollationSQLExpressionsSuite.scala  | 16 ++++++++++++++++
 3 files changed, 23 insertions(+), 6 deletions(-)

diff --git 
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
 
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
index eda65ae48f00..e9fa362de14c 100644
--- 
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
+++ 
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
@@ -200,7 +200,7 @@ object AssertTrue {
   since = "1.6.0",
   group = "misc_funcs")
 case class CurrentDatabase() extends LeafExpression with Unevaluable {
-  override def dataType: DataType = StringType
+  override def dataType: DataType = SQLConf.get.defaultStringType
   override def nullable: Boolean = false
   override def prettyName: String = "current_schema"
   final override val nodePatterns: Seq[TreePattern] = Seq(CURRENT_LIKE)
@@ -219,7 +219,7 @@ case class CurrentDatabase() extends LeafExpression with 
Unevaluable {
   since = "3.1.0",
   group = "misc_funcs")
 case class CurrentCatalog() extends LeafExpression with Unevaluable {
-  override def dataType: DataType = StringType
+  override def dataType: DataType = SQLConf.get.defaultStringType
   override def nullable: Boolean = false
   override def prettyName: String = "current_catalog"
   final override val nodePatterns: Seq[TreePattern] = Seq(CURRENT_LIKE)
@@ -335,7 +335,7 @@ case class TypeOf(child: Expression) extends 
UnaryExpression {
 // scalastyle:on line.size.limit
 case class CurrentUser() extends LeafExpression with Unevaluable {
   override def nullable: Boolean = false
-  override def dataType: DataType = StringType
+  override def dataType: DataType = SQLConf.get.defaultStringType
   override def prettyName: String =
     getTagValue(FunctionRegistry.FUNC_ALIAS).getOrElse("current_user")
   final override val nodePatterns: Seq[TreePattern] = Seq(CURRENT_LIKE)
diff --git 
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/finishAnalysis.scala
 
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/finishAnalysis.scala
index 92ac7599a8ff..48753fbfe326 100644
--- 
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/finishAnalysis.scala
+++ 
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/finishAnalysis.scala
@@ -33,6 +33,7 @@ import org.apache.spark.sql.catalyst.util.DateTimeUtils
 import org.apache.spark.sql.catalyst.util.DateTimeUtils.{convertSpecialDate, 
convertSpecialTimestamp, convertSpecialTimestampNTZ, instantToMicros, 
localDateTimeToMicros}
 import org.apache.spark.sql.catalyst.util.TypeUtils.toSQLExpr
 import org.apache.spark.sql.connector.catalog.CatalogManager
+import org.apache.spark.sql.internal.SQLConf
 import org.apache.spark.sql.types._
 
 
@@ -151,11 +152,11 @@ case class ReplaceCurrentLike(catalogManager: 
CatalogManager) extends Rule[Logic
 
     plan.transformAllExpressionsWithPruning(_.containsPattern(CURRENT_LIKE)) {
       case CurrentDatabase() =>
-        Literal.create(currentNamespace, StringType)
+        Literal.create(currentNamespace, SQLConf.get.defaultStringType)
       case CurrentCatalog() =>
-        Literal.create(currentCatalog, StringType)
+        Literal.create(currentCatalog, SQLConf.get.defaultStringType)
       case CurrentUser() =>
-        Literal.create(currentUser, StringType)
+        Literal.create(currentUser, SQLConf.get.defaultStringType)
     }
   }
 }
diff --git 
a/sql/core/src/test/scala/org/apache/spark/sql/CollationSQLExpressionsSuite.scala
 
b/sql/core/src/test/scala/org/apache/spark/sql/CollationSQLExpressionsSuite.scala
index 37dcdf9bd721..0d48f9f0a88d 100644
--- 
a/sql/core/src/test/scala/org/apache/spark/sql/CollationSQLExpressionsSuite.scala
+++ 
b/sql/core/src/test/scala/org/apache/spark/sql/CollationSQLExpressionsSuite.scala
@@ -997,6 +997,22 @@ class CollationSQLExpressionsSuite
     })
   }
 
+  test("Support CurrentDatabase/Catalog/User expressions with collation") {
+    // Supported collations
+    Seq("UTF8_BINARY_LCASE", "UNICODE", "UNICODE_CI").foreach(collationName =>
+      withSQLConf(SqlApiConf.DEFAULT_COLLATION -> collationName) {
+        val queryDatabase = sql("SELECT current_schema()")
+        val queryCatalog = sql("SELECT current_catalog()")
+        val queryUser = sql("SELECT current_user()")
+        // Data type
+        val dataType = StringType(collationName)
+        assert(queryDatabase.schema.fields.head.dataType.sameType(dataType))
+        assert(queryCatalog.schema.fields.head.dataType.sameType(dataType))
+        assert(queryUser.schema.fields.head.dataType.sameType(dataType))
+      }
+    )
+  }
+
   test("Support Uuid misc expression with collation") {
     // Supported collations
     Seq("UTF8_BINARY_LCASE", "UNICODE", "UNICODE_CI").foreach(collationName =>


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

Reply via email to