This is an automated email from the ASF dual-hosted git repository.
cloud-fan 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 7d4f75a7a32e [SPARK-57752][SPARK-57753][SPARK-57754][4.X][SQL] Assign
names to Hive UDF Java type error conditions
7d4f75a7a32e is described below
commit 7d4f75a7a32e8eedc6c9f94bf85423043250474f
Author: Mitchell <[email protected]>
AuthorDate: Sat Jul 4 11:35:40 2026 +0800
[SPARK-57752][SPARK-57753][SPARK-57754][4.X][SQL] Assign names to Hive UDF
Java type error conditions
### What changes were proposed in this pull request?
This backports apache/spark#56905 to branch-4.x.
It assigns named error conditions and SQLSTATEs for three Hive
UDF/UDAF/UDTF Java type legacy error classes:
- `_LEGACY_ERROR_TEMP_3090` -> `UNSUPPORTED_HIVE_FUNCTION_TYPE.RAW_LIST`
- `_LEGACY_ERROR_TEMP_3091` -> `UNSUPPORTED_HIVE_FUNCTION_TYPE.RAW_MAP`
- `_LEGACY_ERROR_TEMP_3092` -> `UNSUPPORTED_HIVE_FUNCTION_TYPE.WILDCARD`
The branch-4.x backport required resolving an `error-conditions.json`
conflict by preserving branch-4.x's existing `UNSUPPORTED_HIVE_TYPE` entry and
inserting `UNSUPPORTED_HIVE_FUNCTION_TYPE` before it.
### Why are the changes needed?
To keep branch-4.x aligned with master for the named error condition
migration from apache/spark#56905.
### Does this PR introduce _any_ user-facing change?
Yes. The affected Hive UDF/UDAF/UDTF Java type errors now report named
error conditions and SQLSTATEs on branch-4.x, matching master.
### How was this patch tested?
```
./build/sbt "core/testOnly org.apache.spark.SparkThrowableSuite"
./build/sbt "hive/testOnly org.apache.spark.sql.hive.execution.HiveUDFSuite
-- -z UDFRaw"
./build/sbt "hive/testOnly org.apache.spark.sql.hive.execution.HiveUDFSuite
-- -z UDFWildcardList"
jq empty common/utils/src/main/resources/error/error-conditions.json
git diff --check origin/branch-4.x...HEAD
```
### Was this patch authored or co-authored using generative AI tooling?
Generated-by: OpenAI Codex
Closes #56994 from
michaelmitchell-bit/SPARK-57752-branch-4x-hive-udf-errors.
Authored-by: Mitchell <[email protected]>
Signed-off-by: Wenchen Fan <[email protected]>
---
.../src/main/resources/error/error-conditions.json | 38 +++++++++++++---------
.../org/apache/spark/sql/hive/HiveInspectors.scala | 9 +++--
.../spark/sql/hive/execution/HiveUDFSuite.scala | 6 ++--
3 files changed, 32 insertions(+), 21 deletions(-)
diff --git a/common/utils/src/main/resources/error/error-conditions.json
b/common/utils/src/main/resources/error/error-conditions.json
index 4c2e45b25475..8b9292286aab 100644
--- a/common/utils/src/main/resources/error/error-conditions.json
+++ b/common/utils/src/main/resources/error/error-conditions.json
@@ -8641,6 +8641,29 @@
],
"sqlState" : "42K0E"
},
+ "UNSUPPORTED_HIVE_FUNCTION_TYPE" : {
+ "message" : [
+ "Unsupported Hive UDF/UDAF/UDTF Java type:"
+ ],
+ "subClass" : {
+ "RAW_LIST" : {
+ "message" : [
+ "raw java.util.List. Spark cannot infer the element type."
+ ]
+ },
+ "RAW_MAP" : {
+ "message" : [
+ "raw java.util.Map. Spark cannot infer the key and value types."
+ ]
+ },
+ "WILDCARD" : {
+ "message" : [
+ "wildcard type parameter. Spark cannot infer a concrete data type
for wildcard type parameters, such as List<?> or Map<?, ?>."
+ ]
+ }
+ },
+ "sqlState" : "0A000"
+ },
"UNSUPPORTED_HIVE_TYPE" : {
"message" : [
"Cannot read the Hive type <fieldType> of the column <fieldName> because
Spark SQL does not support this data type."
@@ -11389,21 +11412,6 @@
"Corrupted <typeName> in catalog: <numCols> parts expected, but part
<index> is missing."
]
},
- "_LEGACY_ERROR_TEMP_3090" : {
- "message" : [
- "Raw list type in java is unsupported because Spark cannot infer the
element type."
- ]
- },
- "_LEGACY_ERROR_TEMP_3091" : {
- "message" : [
- "Raw map type in java is unsupported because Spark cannot infer key and
value types."
- ]
- },
- "_LEGACY_ERROR_TEMP_3092" : {
- "message" : [
- "Collection types with wildcards (e.g. List<?> or Map<?, ?>) are
unsupported because Spark cannot infer the data type for these type parameters."
- ]
- },
"_LEGACY_ERROR_TEMP_3093" : {
"message" : [
"Unsupported java type <c>"
diff --git
a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
index 285548086a09..b45e8aaa6e63 100644
--- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
+++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala
@@ -241,16 +241,19 @@ private[hive] trait HiveInspectors {
// raw java list type unsupported
case c: Class[_] if isSubClassOf(c, classOf[java.util.List[_]]) =>
throw new AnalysisException(
- errorClass = "_LEGACY_ERROR_TEMP_3090", messageParameters = Map.empty)
+ errorClass = "UNSUPPORTED_HIVE_FUNCTION_TYPE.RAW_LIST",
+ messageParameters = Map.empty)
// raw java map type unsupported
case c: Class[_] if isSubClassOf(c, classOf[java.util.Map[_, _]]) =>
throw new AnalysisException(
- errorClass = "_LEGACY_ERROR_TEMP_3091", messageParameters = Map.empty)
+ errorClass = "UNSUPPORTED_HIVE_FUNCTION_TYPE.RAW_MAP",
+ messageParameters = Map.empty)
case _: WildcardType =>
throw new AnalysisException(
- errorClass = "_LEGACY_ERROR_TEMP_3092", messageParameters = Map.empty)
+ errorClass = "UNSUPPORTED_HIVE_FUNCTION_TYPE.WILDCARD",
+ messageParameters = Map.empty)
case c => throw new AnalysisException(
errorClass = "_LEGACY_ERROR_TEMP_3093", messageParameters = Map("c" ->
c.toString))
diff --git
a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala
b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala
index 53c245394daf..7cf98fae8c8b 100644
---
a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala
+++
b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala
@@ -293,7 +293,7 @@ class HiveUDFSuite extends QueryTest with TestHiveSingleton
{
val err = intercept[AnalysisException](sql("SELECT testUDFRawList(s) FROM
inputTable"))
checkError(
exception = err.getCause.asInstanceOf[AnalysisException],
- condition = "_LEGACY_ERROR_TEMP_3090",
+ condition = "UNSUPPORTED_HIVE_FUNCTION_TYPE.RAW_LIST",
parameters = Map.empty)
sql("DROP TEMPORARY FUNCTION IF EXISTS testUDFRawList")
@@ -309,7 +309,7 @@ class HiveUDFSuite extends QueryTest with TestHiveSingleton
{
val err = intercept[AnalysisException](sql("SELECT testUDFRawMap(s) FROM
inputTable"))
checkError(
exception = err.getCause.asInstanceOf[AnalysisException],
- condition = "_LEGACY_ERROR_TEMP_3091",
+ condition = "UNSUPPORTED_HIVE_FUNCTION_TYPE.RAW_MAP",
parameters = Map.empty)
sql("DROP TEMPORARY FUNCTION IF EXISTS testUDFRawMap")
@@ -325,7 +325,7 @@ class HiveUDFSuite extends QueryTest with TestHiveSingleton
{
val err = intercept[AnalysisException](sql("SELECT testUDFWildcardList(s)
FROM inputTable"))
checkError(
exception = err.getCause.asInstanceOf[AnalysisException],
- condition = "_LEGACY_ERROR_TEMP_3092",
+ condition = "UNSUPPORTED_HIVE_FUNCTION_TYPE.WILDCARD",
parameters = Map.empty)
sql("DROP TEMPORARY FUNCTION IF EXISTS testUDFWildcardList")
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
