[SPARK-40291][SQL] Improve the message for column not in group by clause error

core/src/main/resources/error/error-classes.json

@@ -65,6 +65,12 @@
     ],
     "sqlState" : "22005"
   },
+  "COLUMN_NOT_IN_GROUP_BY_CLAUSE" : {
+    "message" : [
+      "expression '<expression>' is neither present in the group by, nor is it an aggregate function. Add to group by or wrap in first() (or first_value) if you don't care which value you get."
+    ],
+    "sqlState" : "42000"
+  },
   "CONCURRENT_QUERY" : {
     "message" : [
       "Another instance of this query was just started by a concurrent session."

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala

@@ -343,11 +343,7 @@ trait CheckAnalysis extends PredicateHelper with LookupCatalog {
                     s"if you don't care which value you get."
                 )
               case e: Attribute if !groupingExprs.exists(_.semanticEquals(e)) =>
-                failAnalysis(
-                  s"expression '${e.sql}' is neither present in the group by, " +
-                    s"nor is it an aggregate function. " +
-                    "Add to group by or wrap in first() (or first_value) if you don't care " +
-                    "which value you get.")
+                throw QueryCompilationErrors.columnNotInGroupByClauseError(e)
               case s: ScalarSubquery
                   if s.children.nonEmpty && !groupingExprs.exists(_.semanticEquals(s)) =>
                 failAnalysis(s"Correlated scalar subquery '${s.sql}' is neither " +

sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala

@@ -2527,4 +2527,11 @@ private[sql] object QueryCompilationErrors extends QueryErrorsBase {
       errorClass = "INVALID_COLUMN_OR_FIELD_DATA_TYPE",
       messageParameters = Array(toSQLId(name), toSQLType(dt), toSQLType(expected)))
   }
+
+  def columnNotInGroupByClauseError(expression: Expression): Throwable = {
+    new AnalysisException(
+      errorClass = "COLUMN_NOT_IN_GROUP_BY_CLAUSE",
+      messageParameters = Array(expression.sql)
+    )
+  }
 }

sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/AnalysisErrorSuite.scala

@@ -331,7 +331,7 @@ class AnalysisErrorSuite extends AnalysisTest {
   errorTest(
     "missing group by",
     testRelation2.groupBy($"a")($"b"),
-    "'b'" :: "group by" :: Nil
+    "'b'" :: "COLUMN_NOT_IN_GROUP_BY_CLAUSE" :: Nil
   )
 
   errorTest(

sql/core/src/test/resources/sql-tests/results/group-by-filter.sql.out

@@ -228,7 +228,13 @@ SELECT a, COUNT(b) FILTER (WHERE a != 2) FROM testData GROUP BY b
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-expression 'testdata.a' is neither present in the group by, nor is it an aggregate function. Add to group by or wrap in first() (or first_value) if you don't care which value you get.
+{
+  "errorClass" : "COLUMN_NOT_IN_GROUP_BY_CLAUSE",
+  "sqlState" : "42000",
+  "messageParameters" : {
+    "expression" : "testdata.a"
+  }
+}
 
 
 -- !query
@@ -708,7 +714,13 @@ SELECT a + 2, COUNT(b) FILTER (WHERE b IN (1, 2)) FROM testData GROUP BY a + 1
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-expression 'testdata.a' is neither present in the group by, nor is it an aggregate function. Add to group by or wrap in first() (or first_value) if you don't care which value you get.
+{
+  "errorClass" : "COLUMN_NOT_IN_GROUP_BY_CLAUSE",
+  "sqlState" : "42000",
+  "messageParameters" : {
+    "expression" : "testdata.a"
+  }
+}
 
 
 -- !query

sql/core/src/test/resources/sql-tests/results/group-by.sql.out

@@ -43,7 +43,13 @@ SELECT a, COUNT(b) FROM testData GROUP BY b
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-expression 'testdata.a' is neither present in the group by, nor is it an aggregate function. Add to group by or wrap in first() (or first_value) if you don't care which value you get.
+{
+  "errorClass" : "COLUMN_NOT_IN_GROUP_BY_CLAUSE",
+  "sqlState" : "42000",
+  "messageParameters" : {
+    "expression" : "testdata.a"
+  }
+}
 
 
 -- !query
@@ -107,7 +113,13 @@ SELECT a + 2, COUNT(b) FROM testData GROUP BY a + 1
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-expression 'testdata.a' is neither present in the group by, nor is it an aggregate function. Add to group by or wrap in first() (or first_value) if you don't care which value you get.
+{
+  "errorClass" : "COLUMN_NOT_IN_GROUP_BY_CLAUSE",
+  "sqlState" : "42000",
+  "messageParameters" : {
+    "expression" : "testdata.a"
+  }
+}
 
 
 -- !query
@@ -198,7 +210,13 @@ SELECT k AS a, COUNT(v) FROM testDataHasSameNameWithAlias GROUP BY a
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-expression 'testdatahassamenamewithalias.k' is neither present in the group by, nor is it an aggregate function. Add to group by or wrap in first() (or first_value) if you don't care which value you get.
+{
+  "errorClass" : "COLUMN_NOT_IN_GROUP_BY_CLAUSE",
+  "sqlState" : "42000",
+  "messageParameters" : {
+    "expression" : "testdatahassamenamewithalias.k"
+  }
+}
 
 
 -- !query

sql/core/src/test/resources/sql-tests/results/grouping_set.sql.out

@@ -166,7 +166,13 @@ SELECT c1 FROM (values (1,2), (3,2)) t(c1, c2) GROUP BY GROUPING SETS (())
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-expression 't.c1' is neither present in the group by, nor is it an aggregate function. Add to group by or wrap in first() (or first_value) if you don't care which value you get.
+{
+  "errorClass" : "COLUMN_NOT_IN_GROUP_BY_CLAUSE",
+  "sqlState" : "42000",
+  "messageParameters" : {
+    "expression" : "t.c1"
+  }
+}
 
 
 -- !query

sql/core/src/test/resources/sql-tests/results/postgreSQL/create_view.sql.out

@@ -53,7 +53,13 @@ CREATE VIEW key_dependent_view AS
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-expression 'spark_catalog.default.view_base_table.data' is neither present in the group by, nor is it an aggregate function. Add to group by or wrap in first() (or first_value) if you don't care which value you get.
+{
+  "errorClass" : "COLUMN_NOT_IN_GROUP_BY_CLAUSE",
+  "sqlState" : "42000",
+  "messageParameters" : {
+    "expression" : "spark_catalog.default.view_base_table.data"
+  }
+}
 
 
 -- !query

sql/core/src/test/resources/sql-tests/results/udf/udf-group-by.sql.out

@@ -43,7 +43,13 @@ SELECT udf(a), udf(COUNT(udf(b))) FROM testData GROUP BY b
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-expression 'testdata.a' is neither present in the group by, nor is it an aggregate function. Add to group by or wrap in first() (or first_value) if you don't care which value you get.
+{
+  "errorClass" : "COLUMN_NOT_IN_GROUP_BY_CLAUSE",
+  "sqlState" : "42000",
+  "messageParameters" : {
+    "expression" : "testdata.a"
+  }
+}
 
 
 -- !query
@@ -107,7 +113,13 @@ SELECT udf(a + 2), udf(COUNT(b)) FROM testData GROUP BY a + 1
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-expression 'testdata.a' is neither present in the group by, nor is it an aggregate function. Add to group by or wrap in first() (or first_value) if you don't care which value you get.
+{
+  "errorClass" : "COLUMN_NOT_IN_GROUP_BY_CLAUSE",
+  "sqlState" : "42000",
+  "messageParameters" : {
+    "expression" : "testdata.a"
+  }
+}
 
 
 -- !query
@@ -182,7 +194,13 @@ SELECT k AS a, udf(COUNT(udf(v))) FROM testDataHasSameNameWithAlias GROUP BY udf
 struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
-expression 'testdatahassamenamewithalias.k' is neither present in the group by, nor is it an aggregate function. Add to group by or wrap in first() (or first_value) if you don't care which value you get.
+{
+  "errorClass" : "COLUMN_NOT_IN_GROUP_BY_CLAUSE",
+  "sqlState" : "42000",
+  "messageParameters" : {
+    "expression" : "testdatahassamenamewithalias.k"
+  }
+}
 
 
 -- !query

sql/core/src/test/scala/org/apache/spark/sql/execution/SQLViewSuite.scala

@@ -897,10 +897,9 @@ abstract class SQLViewSuite extends QueryTest with SQLTestUtils {
             val e = intercept[AnalysisException] {
               sql("SELECT * FROM v3")
             }.getMessage
-            assert(e.contains(
-              "expression 'spark_catalog.default.t.c1' is neither present " +
-              "in the group by, nor is it an aggregate function. Add to group by or wrap in " +
-              "first() (or first_value) if you don't care which value you get."))
+            assert(
+              e.contains("COLUMN_NOT_IN_GROUP_BY_CLAUSE") &&
+                e.contains("spark_catalog.default.t.c1"))
           }
           withSQLConf(GROUP_BY_ALIASES.key -> "false") {
             val e = intercept[AnalysisException] {