This is an automated email from the ASF dual-hosted git repository.
MaxGekk pushed a commit to branch branch-4.x
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-4.x by this push:
new c456cfea2375 [SPARK-21529][4.X][SQL] Improve the error message for
unsupported Hive union type
c456cfea2375 is described below
commit c456cfea237500ee28a6be7cc1279f2be19c42d6
Author: AgenticSpark <[email protected]>
AuthorDate: Thu Jul 2 10:03:21 2026 +0200
[SPARK-21529][4.X][SQL] Improve the error message for unsupported Hive
union type
### What changes were proposed in this pull request?
Backport of #56775 to `branch-4.x` because the original change conflicts on
this branch.
Detect unsupported Hive `uniontype<...>` values when converting Hive
`FieldSchema` types to Spark SQL types and raise a dedicated
`UNSUPPORTED_HIVE_TYPE` error instead of the generic
`CANNOT_RECOGNIZE_HIVE_TYPE` parser error.
This is a cherry-pick of the merged master commit c90cad6ad2d. The only
conflict was in `error-conditions.json`: `branch-4.x` does not have the
`UNSUPPORTED_HIVE_FUNCTION_TYPE` /
`UNSUPPORTED_HIVE_METASTORE_VERSION_FOR_JAVA` entries that exist on master, so
the new `UNSUPPORTED_HIVE_TYPE` entry is placed directly between
`UNSUPPORTED_GROUPING_EXPRESSION` and `UNSUPPORTED_INSERT`. The Scala changes
apply unchanged.
### Why are the changes needed?
Spark SQL does not support Hive union types. Today the failure message
comes from the parser path and does not clearly identify that the Hive union
type is unsupported.
### Does this PR introduce _any_ user-facing change?
Yes. Reading a Hive table column that uses `uniontype<...>` now reports
`UNSUPPORTED_HIVE_TYPE` with the offending Hive type and column name.
### How was this patch tested?
Cherry-picked from the merged master commit c90cad6ad2d, which passed CI
and review as #56775. The production Scala hunks apply unchanged on
`branch-4.x`; only the `error-conditions.json` entry placement differed and was
re-validated (valid JSON, alphabetical ordering, one structural token per
line). CI here runs `HiveClientImplSuite` and the `SparkThrowableSuite` "Error
conditions are correctly formatted" golden check.
### Was this patch authored or co-authored using generative AI tooling?
Yes. GitHub Copilot assisted with preparing and validating this change.
Closes #56929 from AgenticSpark/agenticspark/SPARK-21529-branch-4.x.
Authored-by: AgenticSpark <[email protected]>
Signed-off-by: Max Gekk <[email protected]>
---
.../src/main/resources/error/error-conditions.json | 6 +++
.../spark/sql/errors/QueryExecutionErrors.scala | 7 ++++
.../spark/sql/hive/client/HiveClientImpl.scala | 5 +++
.../sql/hive/client/HiveClientImplSuite.scala | 49 ++++++++++++++++++++++
4 files changed, 67 insertions(+)
diff --git a/common/utils/src/main/resources/error/error-conditions.json
b/common/utils/src/main/resources/error/error-conditions.json
index 08666ad314fc..5cec6248e1f9 100644
--- a/common/utils/src/main/resources/error/error-conditions.json
+++ b/common/utils/src/main/resources/error/error-conditions.json
@@ -8641,6 +8641,12 @@
],
"sqlState" : "42K0E"
},
+ "UNSUPPORTED_HIVE_TYPE" : {
+ "message" : [
+ "Cannot read the Hive type <fieldType> of the column <fieldName> because
Spark SQL does not support this data type."
+ ],
+ "sqlState" : "0A000"
+ },
"UNSUPPORTED_INSERT" : {
"message" : [
"Can't insert into the target."
diff --git
a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala
b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala
index fda9cc9b2181..41930cafdd2d 100644
---
a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala
+++
b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala
@@ -1696,6 +1696,13 @@ private[sql] object QueryExecutionErrors extends
QueryErrorsBase with ExecutionE
cause = e)
}
+ def unsupportedHiveTypeError(fieldType: String, fieldName: String):
Throwable = {
+ new SparkUnsupportedOperationException(
+ errorClass = "UNSUPPORTED_HIVE_TYPE",
+ messageParameters = Map(
+ "fieldType" -> toSQLType(fieldType),
+ "fieldName" -> toSQLId(fieldName)))
+ }
def getTablesByTypeUnsupportedByHiveVersionError():
SparkUnsupportedOperationException = {
new SparkUnsupportedOperationException(
errorClass = "GET_TABLES_BY_TYPE_UNSUPPORTED_BY_HIVE_VERSION")
diff --git
a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
index 21db79116b52..f09f076707be 100644
---
a/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
+++
b/sql/hive/src/main/scala/org/apache/spark/sql/hive/client/HiveClientImpl.scala
@@ -1139,6 +1139,11 @@ private[hive] object HiveClientImpl extends Logging {
CatalystSqlParser.parseDataType(typeStr)
} catch {
case e: ParseException =>
+ // Hive's union type (uniontype<...>) is not supported by Spark SQL
and makes the parser
+ // fail with a generic message. Detect it and report a clearer error
(SPARK-21529).
+ if (hc.getType.toLowerCase(Locale.ROOT).contains("uniontype<")) {
+ throw QueryExecutionErrors.unsupportedHiveTypeError(hc.getType,
hc.getName)
+ }
throw QueryExecutionErrors.cannotRecognizeHiveTypeError(e, typeStr,
hc.getName)
}
}
diff --git
a/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HiveClientImplSuite.scala
b/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HiveClientImplSuite.scala
new file mode 100644
index 000000000000..9bee44f8f57e
--- /dev/null
+++
b/sql/hive/src/test/scala/org/apache/spark/sql/hive/client/HiveClientImplSuite.scala
@@ -0,0 +1,49 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.hive.client
+
+import org.apache.hadoop.hive.metastore.api.FieldSchema
+
+import org.apache.spark.{SparkFunSuite, SparkUnsupportedOperationException}
+
+class HiveClientImplSuite extends SparkFunSuite {
+
+ test("SPARK-21529: a clear error is raised for an unsupported Hive union
type") {
+ val column = new FieldSchema("c", "uniontype<int,string>", null)
+ checkError(
+ exception = intercept[SparkUnsupportedOperationException] {
+ HiveClientImpl.fromHiveColumn(column)
+ },
+ condition = "UNSUPPORTED_HIVE_TYPE",
+ parameters = Map(
+ "fieldType" -> "\"UNIONTYPE<INT,STRING>\"",
+ "fieldName" -> "`c`"))
+ }
+
+ test("SPARK-21529: a Hive union type nested in a struct is detected") {
+ val column = new FieldSchema("c", "struct<a:uniontype<int,string>>", null)
+ checkError(
+ exception = intercept[SparkUnsupportedOperationException] {
+ HiveClientImpl.fromHiveColumn(column)
+ },
+ condition = "UNSUPPORTED_HIVE_TYPE",
+ parameters = Map(
+ "fieldType" -> "\"STRUCT<A:UNIONTYPE<INT,STRING>>\"",
+ "fieldName" -> "`c`"))
+ }
+}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
