[SPARK-43361][PROTOBUF] update documentation for errors related to en…

…um serialization ### What changes were proposed in this pull request? Follows-up on the comment here: #41075 (comment) Namely: - updates `error-classes.json` and `sql-error-conditions.md` to have the updated error name. - adds an additional test to assert that enum serialization with invalid enum values throws the correct exception. ### Why are the changes needed? Improve documentation ### Does this PR introduce _any_ user-facing change? Yes, documentation. ### How was this patch tested? Existing unit tests Closes #41188 from justaparth/parth/update-documentation-enum-error-message. Authored-by: Parth Upadhyay <parth.upadhyay@gmail.com> Signed-off-by: Ruifeng Zheng <ruifengz@apache.org>
apache · May 19, 2023 · b094b98 · b094b98
1 parent eb2456b
commit b094b98
Show file tree

Hide file tree

Showing 4 changed files with 51 additions and 9 deletions.
diff --git a/connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufSerializer.scala b/connector/protobuf/src/main/scala/org/apache/spark/sql/protobuf/ProtobufSerializer.scala
@@ -120,7 +120,7 @@ private[sql] class ProtobufSerializer(
               catalystPath,
               toFieldStr(protoPath),
               data.toString,
-              enumValues.mkString("", ",", ""))
+              enumValues.mkString(", "))
           }
           fieldDescriptor.getEnumType.findValueByNumber(data)
       case (StringType, STRING) =>

diff --git a/connector/protobuf/src/test/scala/org/apache/spark/sql/protobuf/ProtobufFunctionsSuite.scala b/connector/protobuf/src/test/scala/org/apache/spark/sql/protobuf/ProtobufFunctionsSuite.scala
@@ -1531,6 +1531,48 @@ class ProtobufFunctionsSuite extends QueryTest with SharedSparkSession with Prot
     }
   }
 
+  test("raise enum serialization error") {
+    // Confirm that attempting to serialize an invalid enum value will raise the correct exception.
+    val df = spark.range(1).select(
+      struct(
+        lit("INVALID_VALUE").as("basic_enum")
+      ).as("proto")
+    )
+
+    val dfWithInt = spark.range(1).select(
+      struct(
+        lit(9999).as("basic_enum")
+      ).as("proto")
+    )
+
+    checkWithFileAndClassName("SimpleMessageEnum") { case (name, descFilePathOpt) =>
+      var parseError = intercept[AnalysisException] {
+        df.select(to_protobuf_wrapper($"proto", name, descFilePathOpt)).collect()
+      }
+      checkError(
+        exception = parseError,
+        errorClass = "CANNOT_CONVERT_SQL_VALUE_TO_PROTOBUF_ENUM_TYPE",
+        parameters = Map(
+          "sqlColumn" -> "`basic_enum`",
+          "protobufColumn" -> "field 'basic_enum'",
+          "data" -> "INVALID_VALUE",
+          "enumString" -> "\"NOTHING\", \"FIRST\", \"SECOND\""))
+
+      parseError = intercept[AnalysisException] {
+        dfWithInt.select(to_protobuf_wrapper($"proto", name, descFilePathOpt)).collect()
+      }
+      checkError(
+        exception = parseError,
+        errorClass = "CANNOT_CONVERT_SQL_VALUE_TO_PROTOBUF_ENUM_TYPE",
+        parameters = Map(
+          "sqlColumn" -> "`basic_enum`",
+          "protobufColumn" -> "field 'basic_enum'",
+          "data" -> "9999",
+          "enumString" -> "0, 1, 2"))
+    }
+  }
+
+
   def testFromProtobufWithOptions(
     df: DataFrame,
     expectedDf: DataFrame,

diff --git a/core/src/main/resources/error/error-classes.json b/core/src/main/resources/error/error-classes.json
@@ -62,14 +62,14 @@
       "Unable to convert <protobufType> of Protobuf to SQL type <toType>."
     ]
   },
-  "CANNOT_CONVERT_SQL_TYPE_TO_PROTOBUF_ENUM_TYPE" : {
+  "CANNOT_CONVERT_SQL_TYPE_TO_PROTOBUF_FIELD_TYPE" : {
     "message" : [
-      "Cannot convert SQL <sqlColumn> to Protobuf <protobufColumn> because <data> cannot be written since it's not defined in ENUM <enumString>."
+      "Cannot convert SQL <sqlColumn> to Protobuf <protobufColumn> because schema is incompatible (protobufType = <protobufType>, sqlType = <sqlType>)."
     ]
   },
-  "CANNOT_CONVERT_SQL_TYPE_TO_PROTOBUF_FIELD_TYPE" : {
+  "CANNOT_CONVERT_SQL_VALUE_TO_PROTOBUF_ENUM_TYPE" : {
     "message" : [
-      "Cannot convert SQL <sqlColumn> to Protobuf <protobufColumn> because schema is incompatible (protobufType = <protobufType>, sqlType = <sqlType>)."
+      "Cannot convert SQL <sqlColumn> to Protobuf <protobufColumn> because <data> is not in defined values for enum: <enumString>."
     ]
   },
   "CANNOT_DECODE_URL" : {

diff --git a/docs/sql-error-conditions.md b/docs/sql-error-conditions.md
@@ -77,17 +77,17 @@ SQLSTATE: none assigned
 
 Unable to convert `<protobufType>` of Protobuf to SQL type `<toType>`.
 
-### CANNOT_CONVERT_SQL_TYPE_TO_PROTOBUF_ENUM_TYPE
+### CANNOT_CONVERT_SQL_TYPE_TO_PROTOBUF_FIELD_TYPE
 
 SQLSTATE: none assigned
 
-Cannot convert SQL `<sqlColumn>` to Protobuf `<protobufColumn>` because `<data>` cannot be written since it's not defined in ENUM `<enumString>`.
+Cannot convert SQL `<sqlColumn>` to Protobuf `<protobufColumn>` because schema is incompatible (protobufType = `<protobufType>`, sqlType = `<sqlType>`).
 
-### CANNOT_CONVERT_SQL_TYPE_TO_PROTOBUF_FIELD_TYPE
+### CANNOT_CONVERT_SQL_VALUE_TO_PROTOBUF_ENUM_TYPE
 
 SQLSTATE: none assigned
 
-Cannot convert SQL `<sqlColumn>` to Protobuf `<protobufColumn>` because schema is incompatible (protobufType = `<protobufType>`, sqlType = `<sqlType>`).
+Cannot convert SQL `<sqlColumn>` to Protobuf `<protobufColumn>` because `<data>` is not in defined values for enum: `<enumString>`.
 
 ### CANNOT_DECODE_URL