[SPARK-44987][SQL] Assign a name to the error class `_LEGACY_ERROR_TE…

…MP_1100` ### What changes were proposed in this pull request? In the PR, I propose to assign the name `NON_FOLDABLE_ARGUMENT` to the legacy error class `_LEGACY_ERROR_TEMP_1100`, and improve the error message format: make it less restrictive. ### Why are the changes needed? 1. To don't confuse users by slightly restrictive error message about literals. 2. To assign proper name as a part of activity in SPARK-37935 ### Does this PR introduce _any_ user-facing change? No. Only if user's code depends on error class name and message parameters. ### How was this patch tested? By running the modified and affected tests: ``` $ build/sbt "test:testOnly *.StringFunctionsSuite" $ PYSPARK_PYTHON=python3 build/sbt "sql/testOnly org.apache.spark.sql.SQLQueryTestSuite" $ build/sbt "core/testOnly *SparkThrowableSuite" ``` ### Was this patch authored or co-authored using generative AI tooling? No. Closes #42737 from MaxGekk/assign-name-_LEGACY_ERROR_TEMP_1100. Authored-by: Max Gekk <[email protected]> Signed-off-by: Max Gekk <[email protected]>
apache · Aug 31, 2023 · e72ce91 · e72ce91
1 parent 723a0aa
commit e72ce91
Show file tree

Hide file tree

Showing 11 changed files with 88 additions and 67 deletions.
diff --git a/common/utils/src/main/resources/error/error-classes.json b/common/utils/src/main/resources/error/error-classes.json
@@ -2215,6 +2215,12 @@
     ],
     "sqlState" : "42607"
   },
+  "NON_FOLDABLE_ARGUMENT" : {
+    "message" : [
+      "The function <funcName> requires the parameter <paramName> to be a foldable expression of the type <paramType>, but the actual argument is a non-foldable."
+    ],
+    "sqlState" : "22024"
+  },
   "NON_LAST_MATCHED_CLAUSE_OMIT_CONDITION" : {
     "message" : [
       "When there are more than one MATCHED clauses in a MERGE statement, only the last MATCHED clause can omit the condition."
@@ -4029,11 +4035,6 @@
       "<funcName>() doesn't support the <mode> mode. Acceptable modes are <permissiveMode> and <failFastMode>."
     ]
   },
-  "_LEGACY_ERROR_TEMP_1100" : {
-    "message" : [
-      "The '<argName>' parameter of function '<funcName>' needs to be a <requiredType> literal."
-    ]
-  },
   "_LEGACY_ERROR_TEMP_1103" : {
     "message" : [
       "Unsupported component type <clz> in arrays."

diff --git a/docs/sql-error-conditions.md b/docs/sql-error-conditions.md
@@ -1305,6 +1305,12 @@ Cannot call function `<functionName>` because named argument references are not
 
 It is not allowed to use an aggregate function in the argument of another aggregate function. Please use the inner aggregate function in a sub-query.
 
+### NON_FOLDABLE_ARGUMENT
+
+[SQLSTATE: 22024](sql-error-conditions-sqlstates.html#class-22-data-exception)
+
+The function `<funcName>` requires the parameter `<paramName>` to be a foldable expression of the type `<paramType>`, but the actual argument is a non-foldable.
+
 ### NON_LAST_MATCHED_CLAUSE_OMIT_CONDITION
 
 [SQLSTATE: 42613](sql-error-conditions-sqlstates.html#class-42-syntax-error-or-access-rule-violation)

diff --git a/...talyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala b/...talyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/datetimeExpressions.scala
@@ -2934,7 +2934,7 @@ object Extract {
         }
       }
     } else {
-      throw QueryCompilationErrors.requireLiteralParameter(funcName, "field", "string")
+      throw QueryCompilationErrors.nonFoldableArgumentError(funcName, "field", StringType)
     }
   }
 }

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/mathExpressions.scala
@@ -283,10 +283,10 @@ trait CeilFloorExpressionBuilderBase extends ExpressionBuilder {
     } else if (numArgs == 2) {
       val scale = expressions(1)
       if (!(scale.foldable && scale.dataType == IntegerType)) {
-        throw QueryCompilationErrors.requireLiteralParameter(funcName, "scale", "int")
+        throw QueryCompilationErrors.nonFoldableArgumentError(funcName, "scale", IntegerType)
       }
       if (scale.eval() == null) {
-        throw QueryCompilationErrors.requireLiteralParameter(funcName, "scale", "int")
+        throw QueryCompilationErrors.nonFoldableArgumentError(funcName, "scale", IntegerType)
       }
       buildWithTwoParams(expressions(0), scale)
     } else {

diff --git a/...st/src/main/scala/org/apache/spark/sql/catalyst/expressions/numberFormatExpressions.scala b/...st/src/main/scala/org/apache/spark/sql/catalyst/expressions/numberFormatExpressions.scala
@@ -247,7 +247,7 @@ object ToCharacterBuilder extends ExpressionBuilder {
         case _: DatetimeType => DateFormatClass(inputExpr, format)
         case _: BinaryType =>
           if (!(format.dataType == StringType && format.foldable)) {
-            throw QueryCompilationErrors.requireLiteralParameter(funcName, "format", "string")
+            throw QueryCompilationErrors.nonFoldableArgumentError(funcName, "format", StringType)
           }
           format.eval().asInstanceOf[UTF8String].toString.toLowerCase(Locale.ROOT).trim match {
             case "base64" => Base64(inputExpr)

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryCompilationErrors.scala
@@ -1207,14 +1207,16 @@ private[sql] object QueryCompilationErrors extends QueryErrorsBase with Compilat
         "failFastMode" -> FailFastMode.name))
   }
 
-  def requireLiteralParameter(
-      funcName: String, argName: String, requiredType: String): Throwable = {
+  def nonFoldableArgumentError(
+      funcName: String,
+      paramName: String,
+      paramType: DataType): Throwable = {
     new AnalysisException(
-      errorClass = "_LEGACY_ERROR_TEMP_1100",
+      errorClass = "NON_FOLDABLE_ARGUMENT",
       messageParameters = Map(
-        "argName" -> argName,
-        "funcName" -> funcName,
-        "requiredType" -> requiredType))
+        "funcName" -> toSQLId(funcName),
+        "paramName" -> toSQLId(paramName),
+        "paramType" -> toSQLType(paramType)))
   }
 
   def literalTypeUnsupportedForSourceTypeError(field: String, source: Expression): Throwable = {

diff --git a/sql/core/src/test/resources/sql-tests/analyzer-results/ceil-floor-with-scale-param.sql.out b/sql/core/src/test/resources/sql-tests/analyzer-results/ceil-floor-with-scale-param.sql.out
@@ -81,11 +81,12 @@ SELECT CEIL(2.5, null)
 -- !query analysis
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1100",
+  "errorClass" : "NON_FOLDABLE_ARGUMENT",
+  "sqlState" : "22024",
   "messageParameters" : {
-    "argName" : "scale",
-    "funcName" : "ceil",
-    "requiredType" : "int"
+    "funcName" : "`ceil`",
+    "paramName" : "`scale`",
+    "paramType" : "\"INT\""
   },
   "queryContext" : [ {
     "objectType" : "",
@@ -102,11 +103,12 @@ SELECT CEIL(2.5, 'a')
 -- !query analysis
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1100",
+  "errorClass" : "NON_FOLDABLE_ARGUMENT",
+  "sqlState" : "22024",
   "messageParameters" : {
-    "argName" : "scale",
-    "funcName" : "ceil",
-    "requiredType" : "int"
+    "funcName" : "`ceil`",
+    "paramName" : "`scale`",
+    "paramType" : "\"INT\""
   },
   "queryContext" : [ {
     "objectType" : "",
@@ -223,11 +225,12 @@ SELECT FLOOR(2.5, null)
 -- !query analysis
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1100",
+  "errorClass" : "NON_FOLDABLE_ARGUMENT",
+  "sqlState" : "22024",
   "messageParameters" : {
-    "argName" : "scale",
-    "funcName" : "floor",
-    "requiredType" : "int"
+    "funcName" : "`floor`",
+    "paramName" : "`scale`",
+    "paramType" : "\"INT\""
   },
   "queryContext" : [ {
     "objectType" : "",
@@ -244,11 +247,12 @@ SELECT FLOOR(2.5, 'a')
 -- !query analysis
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1100",
+  "errorClass" : "NON_FOLDABLE_ARGUMENT",
+  "sqlState" : "22024",
   "messageParameters" : {
-    "argName" : "scale",
-    "funcName" : "floor",
-    "requiredType" : "int"
+    "funcName" : "`floor`",
+    "paramName" : "`scale`",
+    "paramType" : "\"INT\""
   },
   "queryContext" : [ {
     "objectType" : "",

diff --git a/sql/core/src/test/resources/sql-tests/analyzer-results/extract.sql.out b/sql/core/src/test/resources/sql-tests/analyzer-results/extract.sql.out
@@ -932,11 +932,12 @@ select date_part(c, c) from t
 -- !query analysis
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1100",
+  "errorClass" : "NON_FOLDABLE_ARGUMENT",
+  "sqlState" : "22024",
   "messageParameters" : {
-    "argName" : "field",
-    "funcName" : "date_part",
-    "requiredType" : "string"
+    "funcName" : "`date_part`",
+    "paramName" : "`field`",
+    "paramType" : "\"STRING\""
   },
   "queryContext" : [ {
     "objectType" : "",
@@ -964,11 +965,12 @@ select date_part(i, i) from t
 -- !query analysis
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1100",
+  "errorClass" : "NON_FOLDABLE_ARGUMENT",
+  "sqlState" : "22024",
   "messageParameters" : {
-    "argName" : "field",
-    "funcName" : "date_part",
-    "requiredType" : "string"
+    "funcName" : "`date_part`",
+    "paramName" : "`field`",
+    "paramType" : "\"STRING\""
   },
   "queryContext" : [ {
     "objectType" : "",

diff --git a/sql/core/src/test/resources/sql-tests/results/ceil-floor-with-scale-param.sql.out b/sql/core/src/test/resources/sql-tests/results/ceil-floor-with-scale-param.sql.out
@@ -94,11 +94,12 @@ struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1100",
+  "errorClass" : "NON_FOLDABLE_ARGUMENT",
+  "sqlState" : "22024",
   "messageParameters" : {
-    "argName" : "scale",
-    "funcName" : "ceil",
-    "requiredType" : "int"
+    "funcName" : "`ceil`",
+    "paramName" : "`scale`",
+    "paramType" : "\"INT\""
   },
   "queryContext" : [ {
     "objectType" : "",
@@ -117,11 +118,12 @@ struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1100",
+  "errorClass" : "NON_FOLDABLE_ARGUMENT",
+  "sqlState" : "22024",
   "messageParameters" : {
-    "argName" : "scale",
-    "funcName" : "ceil",
-    "requiredType" : "int"
+    "funcName" : "`ceil`",
+    "paramName" : "`scale`",
+    "paramType" : "\"INT\""
   },
   "queryContext" : [ {
     "objectType" : "",
@@ -253,11 +255,12 @@ struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1100",
+  "errorClass" : "NON_FOLDABLE_ARGUMENT",
+  "sqlState" : "22024",
   "messageParameters" : {
-    "argName" : "scale",
-    "funcName" : "floor",
-    "requiredType" : "int"
+    "funcName" : "`floor`",
+    "paramName" : "`scale`",
+    "paramType" : "\"INT\""
   },
   "queryContext" : [ {
     "objectType" : "",
@@ -276,11 +279,12 @@ struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1100",
+  "errorClass" : "NON_FOLDABLE_ARGUMENT",
+  "sqlState" : "22024",
   "messageParameters" : {
-    "argName" : "scale",
-    "funcName" : "floor",
-    "requiredType" : "int"
+    "funcName" : "`floor`",
+    "paramName" : "`scale`",
+    "paramType" : "\"INT\""
   },
   "queryContext" : [ {
     "objectType" : "",

diff --git a/sql/core/src/test/resources/sql-tests/results/extract.sql.out b/sql/core/src/test/resources/sql-tests/results/extract.sql.out
@@ -714,11 +714,12 @@ struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1100",
+  "errorClass" : "NON_FOLDABLE_ARGUMENT",
+  "sqlState" : "22024",
   "messageParameters" : {
-    "argName" : "field",
-    "funcName" : "date_part",
-    "requiredType" : "string"
+    "funcName" : "`date_part`",
+    "paramName" : "`field`",
+    "paramType" : "\"STRING\""
   },
   "queryContext" : [ {
     "objectType" : "",
@@ -745,11 +746,12 @@ struct<>
 -- !query output
 org.apache.spark.sql.AnalysisException
 {
-  "errorClass" : "_LEGACY_ERROR_TEMP_1100",
+  "errorClass" : "NON_FOLDABLE_ARGUMENT",
+  "sqlState" : "22024",
   "messageParameters" : {
-    "argName" : "field",
-    "funcName" : "date_part",
-    "requiredType" : "string"
+    "funcName" : "`date_part`",
+    "paramName" : "`field`",
+    "paramType" : "\"STRING\""
   },
   "queryContext" : [ {
     "objectType" : "",

diff --git a/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala
@@ -875,11 +875,11 @@ class StringFunctionsSuite extends QueryTest with SharedSparkSession {
         exception = intercept[AnalysisException] {
           df2.select(func(col("input"), col("format"))).collect()
         },
-        errorClass = "_LEGACY_ERROR_TEMP_1100",
+        errorClass = "NON_FOLDABLE_ARGUMENT",
         parameters = Map(
-          "argName" -> "format",
-          "funcName" -> funcName,
-          "requiredType" -> "string"))
+          "funcName" -> s"`$funcName`",
+          "paramName" -> "`format`",
+          "paramType" -> "\"STRING\""))
       checkError(
         exception = intercept[AnalysisException] {
           df2.select(func(col("input"), lit("invalid_format"))).collect()
-Original file line number
+Diff line change
@@ Expand Up / @@ -2934,7 +2934,7 @@ object Extract { @@
             }
           }
         } else {
-          throw QueryCompilationErrors.requireLiteralParameter(funcName, "field", "string")
+          throw QueryCompilationErrors.nonFoldableArgumentError(funcName, "field", StringType)
         }
       }
     }
@@ Expand Down @@