[SPARK-56569] Add WINDOW_FUNCTION_FRAME_NOT_ORDERED error to replace _LEGACY_ERROR_TEMP_1037

common/utils/src/main/resources/error/error-conditions.json

@@ -8530,6 +8530,12 @@
     ],
     "sqlState" : "42K0E"
   },
+  "WINDOW_FUNCTION_FRAME_NOT_ORDERED" : {
+    "message" : [
+      "Window function <wf_name> requires the window to be ordered. You need to add an ORDER BY clause. For example: SELECT <wf_expr> OVER (PARTITION BY window_partition ORDER BY window_ordering) FROM table."
+    ],
+    "sqlState" : "42601"
+  },
   "WINDOW_FUNCTION_NOT_ALLOWED_IN_CLAUSE" : {
     "message" : [
       "It is not allowed to use window functions inside <clauseName> clause."
@@ -8801,11 +8807,6 @@
       "Window Frame <wf> must match the required frame <required>."
     ]
   },
-  "_LEGACY_ERROR_TEMP_1037" : {
-    "message" : [
-      "Window function <wf> requires window to be ordered, please add ORDER BY clause. For example SELECT <wf>(value_expr) OVER (PARTITION BY window_partition ORDER BY window_ordering) from table."
-    ]
-  },
   "_LEGACY_ERROR_TEMP_1039" : {
     "message" : [
       "Multiple time/session window expressions would result in a cartesian product of rows, therefore they are currently not supported."

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

@@ -884,8 +884,10 @@ private[sql] object QueryCompilationErrors extends QueryErrorsBase with Compilat
 
   def windowFunctionWithWindowFrameNotOrderedError(wf: WindowFunction): Throwable = {
     new AnalysisException(
-      errorClass = "_LEGACY_ERROR_TEMP_1037",
-      messageParameters = Map("wf" -> wf.toString))
+      errorClass = "WINDOW_FUNCTION_FRAME_NOT_ORDERED",
+      messageParameters = Map(
+        "wf_name" -> wf.prettyName,
+        "wf_expr" -> wf.sql))
   }
 
   def multiTimeWindowExpressionsNotSupportedError(t: TreeNode[_]): Throwable = {

sql/core/src/test/resources/sql-tests/analyzer-results/udf/udf-window.sql.out

@@ -421,9 +421,11 @@ SELECT udf(val), cate, row_number() OVER(PARTITION BY cate) FROM testData ORDER
 -- !query analysis
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1037",
+  "errorClass" : "WINDOW_FUNCTION_FRAME_NOT_ORDERED",
+  "sqlState" : "42601",
   "messageParameters" : {
-    "wf" : "row_number()"
+    "wf_expr" : "row_number()",
+    "wf_name" : "row_number"
   }
 }
 

sql/core/src/test/resources/sql-tests/analyzer-results/window.sql.out

@@ -616,9 +616,26 @@ SELECT val, cate, row_number() OVER(PARTITION BY cate) FROM testData ORDER BY ca
 -- !query analysis
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1037",
+  "errorClass" : "WINDOW_FUNCTION_FRAME_NOT_ORDERED",
+  "sqlState" : "42601",
   "messageParameters" : {
-    "wf" : "row_number()"
+    "wf_expr" : "row_number()",
+    "wf_name" : "row_number"
+  }
+}
+
+
+-- !query
+SELECT lead(t) OVER ()
+FROM VALUES ('A'), ('B'), ('C') AS tbl(t)
+-- !query analysis
+org.apache.spark.sql.AnalysisException
+{
+  "errorClass" : "WINDOW_FUNCTION_FRAME_NOT_ORDERED",
+  "sqlState" : "42601",
+  "messageParameters" : {
+    "wf_expr" : "lead(tbl.t, 1, NULL)",
+    "wf_name" : "lead"
   }
 }
 

sql/core/src/test/resources/sql-tests/inputs/window.sql

@@ -158,6 +158,10 @@ SELECT val, cate, avg(null) OVER(PARTITION BY cate ORDER BY val) FROM testData O
 -- OrderBy not specified
 SELECT val, cate, row_number() OVER(PARTITION BY cate) FROM testData ORDER BY cate, val;
 
+-- OrderBy not specified for lead
+SELECT lead(t) OVER ()
+FROM VALUES ('A'), ('B'), ('C') AS tbl(t);
+
 -- Over clause is empty
 SELECT val, cate, sum(val) OVER(), avg(val) OVER() FROM testData ORDER BY cate, val;
 

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

@@ -421,9 +421,11 @@ struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1037",
+  "errorClass" : "WINDOW_FUNCTION_FRAME_NOT_ORDERED",
+  "sqlState" : "42601",
   "messageParameters" : {
-    "wf" : "row_number()"
+    "wf_expr" : "row_number()",
+    "wf_name" : "row_number"
   }
 }
 

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

@@ -599,9 +599,28 @@ struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1037",
+  "errorClass" : "WINDOW_FUNCTION_FRAME_NOT_ORDERED",
+  "sqlState" : "42601",
   "messageParameters" : {
-    "wf" : "row_number()"
+    "wf_expr" : "row_number()",
+    "wf_name" : "row_number"
+  }
+}
+
+
+-- !query
+SELECT lead(t) OVER ()
+FROM VALUES ('A'), ('B'), ('C') AS tbl(t)
+-- !query schema
+struct<>
+-- !query output
+org.apache.spark.sql.AnalysisException
+{
+  "errorClass" : "WINDOW_FUNCTION_FRAME_NOT_ORDERED",
+  "sqlState" : "42601",
+  "messageParameters" : {
+    "wf_expr" : "lead(tbl.t, 1, NULL)",
+    "wf_name" : "lead"
   }
 }
 

sql/core/src/test/scala/org/apache/spark/sql/DataFrameWindowFunctionsSuite.scala

@@ -71,10 +71,12 @@ class DataFrameWindowFunctionsSuite extends QueryTest
 
   test("window function should fail if order by clause is not specified") {
     val df = Seq((1, "1"), (2, "2"), (1, "2"), (2, "2")).toDF("key", "value")
-    val e = intercept[AnalysisException](
-      // Here we missed .orderBy("key")!
-      df.select(row_number().over(Window.partitionBy("value"))).collect())
-    assert(e.message.contains("requires window to be ordered"))
+    checkError(
+      exception = intercept[AnalysisException](
+        // Here we missed .orderBy("key")!
+        df.select(row_number().over(Window.partitionBy("value"))).collect()),
+      condition = "WINDOW_FUNCTION_FRAME_NOT_ORDERED",
+      parameters = Map("wf_name" -> "row_number", "wf_expr" -> "row_number()"))
   }
 
   test("corr, covar_pop, stddev_pop functions in specific window") {