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 5eed8810eb54 [SPARK-57745][SQL] Assign named error class for
unsupported datatype
5eed8810eb54 is described below
commit 5eed8810eb54a2235e106a32a1cb9b55090c3811
Author: michaelmitchell-bit <[email protected]>
AuthorDate: Mon Jun 29 20:30:23 2026 +0200
[SPARK-57745][SQL] Assign named error class for unsupported datatype
### What changes were proposed in this pull request?
This PR replaces the legacy error class `_LEGACY_ERROR_TEMP_3192` with the
existing named error condition `UNSUPPORTED_DATATYPE` in vectorized row/column
conversion paths. It also removes the legacy error condition entry and adds
regression coverage for the migrated error class.
### Why are the changes needed?
`_LEGACY_ERROR_TEMP_3192` is one of the temporary legacy error classes
tracked by SPARK-57745. Reusing `UNSUPPORTED_DATATYPE` gives this unsupported
datatype path a stable named error condition and SQLSTATE.
### Does this PR introduce any user-facing change?
Yes, on the `SparkThrowable` surface for these unsupported datatype errors.
The error class changes from `_LEGACY_ERROR_TEMP_3192` to
`UNSUPPORTED_DATATYPE`, the SQLSTATE changes from absent to `0A000`, and the
message now uses the standard `UNSUPPORTED_DATATYPE` text with SQL-formatted
type names.
### How was this patch tested?
Ran:
`./build/sbt "sql/testOnly
org.apache.spark.sql.errors.QueryExecutionErrorsSuite -- -z SPARK-57745"`
Also verified the error condition JSON still parses and no
`_LEGACY_ERROR_TEMP_3192` references remain in the touched files.
### Was this patch authored or co-authored using generative AI tooling?
Generated-by: OpenAI Codex
### License
This contribution is my original work and I license it to the project under
the project's open source license.
Closes #56857 from michaelmitchell-bit/SPARK-57745-named-error-class.
Authored-by: michaelmitchell-bit <[email protected]>
Signed-off-by: Max Gekk <[email protected]>
(cherry picked from commit 9eced1be4842152c904bfcf2a0bc7b042b8d61e0)
Signed-off-by: Max Gekk <[email protected]>
---
.../src/main/resources/error/error-conditions.json | 5 --
.../execution/vectorized/ColumnVectorUtils.java | 3 +-
.../execution/vectorized/MutableColumnarRow.java | 5 +-
.../sql/errors/QueryExecutionErrorsSuite.scala | 79 +++++++++++++++++++++-
4 files changed, 82 insertions(+), 10 deletions(-)
diff --git a/common/utils/src/main/resources/error/error-conditions.json
b/common/utils/src/main/resources/error/error-conditions.json
index c7e4b5c5ddec..286595dc11d3 100644
--- a/common/utils/src/main/resources/error/error-conditions.json
+++ b/common/utils/src/main/resources/error/error-conditions.json
@@ -11608,11 +11608,6 @@
"Dictionary encoding does not support String"
]
},
- "_LEGACY_ERROR_TEMP_3192" : {
- "message" : [
- "Datatype not supported <dt>"
- ]
- },
"_LEGACY_ERROR_TEMP_3198" : {
"message" : [
"Cannot grow BufferHolder by size <neededSize> because the size is
negative"
diff --git
a/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ColumnVectorUtils.java
b/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ColumnVectorUtils.java
index 2e57d37c9f80..44a50fc3f702 100644
---
a/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ColumnVectorUtils.java
+++
b/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/ColumnVectorUtils.java
@@ -34,6 +34,7 @@ import org.apache.spark.sql.catalyst.InternalRow;
import org.apache.spark.sql.catalyst.expressions.GenericInternalRow;
import org.apache.spark.sql.catalyst.types.*;
import org.apache.spark.sql.catalyst.util.DateTimeUtils;
+import org.apache.spark.sql.errors.QueryExecutionErrors;
import org.apache.spark.sql.execution.RowToColumnConverter;
import org.apache.spark.sql.types.*;
import org.apache.spark.sql.vectorized.ColumnarArray;
@@ -237,7 +238,7 @@ public class ColumnVectorUtils {
dst.appendLong(DateTimeUtils.localDateTimeToMicros((LocalDateTime) o));
} else {
throw new SparkUnsupportedOperationException(
- "_LEGACY_ERROR_TEMP_3192", Map.of("dt", t.toString()));
+ "UNSUPPORTED_DATATYPE", Map.of("typeName",
QueryExecutionErrors.toSQLType(t)));
}
}
}
diff --git
a/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java
b/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java
index de391897c24a..6134530dc5d2 100644
---
a/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java
+++
b/sql/core/src/main/java/org/apache/spark/sql/execution/vectorized/MutableColumnarRow.java
@@ -23,6 +23,7 @@ import java.util.Map;
import org.apache.spark.SparkUnsupportedOperationException;
import org.apache.spark.sql.catalyst.InternalRow;
import org.apache.spark.sql.catalyst.expressions.GenericInternalRow;
+import org.apache.spark.sql.errors.QueryExecutionErrors;
import org.apache.spark.sql.types.*;
import org.apache.spark.sql.vectorized.ColumnarArray;
import org.apache.spark.sql.vectorized.ColumnarBatch;
@@ -234,7 +235,7 @@ public final class MutableColumnarRow extends InternalRow {
return getTimestampLTZNanos(ordinal);
} else {
throw new SparkUnsupportedOperationException(
- "_LEGACY_ERROR_TEMP_3192", Map.of("dt", dataType.toString()));
+ "UNSUPPORTED_DATATYPE", Map.of("typeName",
QueryExecutionErrors.toSQLType(dataType)));
}
}
@@ -267,7 +268,7 @@ public final class MutableColumnarRow extends InternalRow {
setTimestampLTZNanos(ordinal, (TimestampNanosVal) value);
} else {
throw new SparkUnsupportedOperationException(
- "_LEGACY_ERROR_TEMP_3192", Map.of("dt", dt.toString()));
+ "UNSUPPORTED_DATATYPE", Map.of("typeName",
QueryExecutionErrors.toSQLType(dt)));
}
}
}
diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/errors/QueryExecutionErrorsSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/errors/QueryExecutionErrorsSuite.scala
index 058b47ee4f67..c5b6a2335035 100644
---
a/sql/core/src/test/scala/org/apache/spark/sql/errors/QueryExecutionErrorsSuite.scala
+++
b/sql/core/src/test/scala/org/apache/spark/sql/errors/QueryExecutionErrorsSuite.scala
@@ -18,6 +18,7 @@
package org.apache.spark.sql.errors
import java.io.{File, IOException}
+import java.lang.reflect.InvocationTargetException
import java.net.{URI, URL}
import java.sql.{Connection, DatabaseMetaData, Driver, DriverManager,
PreparedStatement, ResultSet, ResultSetMetaData}
import java.time.LocalDateTime
@@ -48,15 +49,32 @@ import
org.apache.spark.sql.execution.datasources.orc.OrcTest
import org.apache.spark.sql.execution.datasources.parquet.ParquetTest
import org.apache.spark.sql.execution.datasources.v2.jdbc.JDBCTableCatalog
import
org.apache.spark.sql.execution.streaming.checkpointing.FileSystemBasedCheckpointFileManager
-import org.apache.spark.sql.execution.vectorized.ConstantColumnVector
+import org.apache.spark.sql.execution.vectorized.{
+ ColumnVectorUtils,
+ ConstantColumnVector,
+ MutableColumnarRow,
+ OnHeapColumnVector,
+ WritableColumnVector}
import org.apache.spark.sql.functions.{lit, lower, struct, sum, udf}
import org.apache.spark.sql.internal.LegacyBehaviorPolicy.EXCEPTION
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.jdbc.{JdbcDialect, JdbcDialects}
import org.apache.spark.sql.streaming.StreamingQueryException
import org.apache.spark.sql.test.SharedSparkSession
-import org.apache.spark.sql.types.{ArrayType, BooleanType, DataType,
DecimalType, IntegerType, LongType, MetadataBuilder, StructField, StructType,
TimestampNTZNanosType}
+import org.apache.spark.sql.types.{
+ ArrayType,
+ BooleanType,
+ DataType,
+ DecimalType,
+ IntegerType,
+ LongType,
+ MetadataBuilder,
+ ObjectType,
+ StructField,
+ StructType,
+ TimestampNTZNanosType}
import org.apache.spark.sql.vectorized.ColumnarArray
+import org.apache.spark.sql.vectorized.ColumnVector
import org.apache.spark.unsafe.array.ByteArrayMethods.MAX_ROUNDED_ARRAY_LENGTH
import org.apache.spark.util.ThreadUtils
import org.apache.spark.util.Utils
@@ -869,6 +887,63 @@ class QueryExecutionErrorsSuite
sqlState = "0A000")
}
+ test("SPARK-57745: unsupported datatype in ColumnVectorUtils.appendValue") {
+ val objectType = ObjectType(classOf[java.lang.Integer])
+ val column = new OnHeapColumnVector(1, IntegerType)
+ try {
+ val appendValue = classOf[ColumnVectorUtils].getDeclaredMethod(
+ "appendValue",
+ classOf[WritableColumnVector],
+ classOf[DataType],
+ classOf[Object])
+ appendValue.setAccessible(true)
+
+ checkError(
+ exception = intercept[SparkUnsupportedOperationException] {
+ try {
+ appendValue.invoke(null, column, objectType, Integer.valueOf(1))
+ } catch {
+ case e: InvocationTargetException => throw e.getCause
+ }
+ },
+ condition = "UNSUPPORTED_DATATYPE",
+ parameters = Map("typeName" -> toSQLType(objectType)),
+ sqlState = "0A000")
+ } finally {
+ column.close()
+ }
+ }
+
+ test("SPARK-57745: unsupported datatype in MutableColumnarRow.get and
update") {
+ val objectType = ObjectType(classOf[java.lang.Integer])
+ val column = new OnHeapColumnVector(1, IntegerType)
+ try {
+ val dataTypeField = classOf[ColumnVector].getDeclaredField("type")
+ dataTypeField.setAccessible(true)
+ dataTypeField.set(column, objectType)
+
+ val row = new MutableColumnarRow(Array[WritableColumnVector](column))
+
+ checkError(
+ exception = intercept[SparkUnsupportedOperationException] {
+ row.get(0, objectType)
+ },
+ condition = "UNSUPPORTED_DATATYPE",
+ parameters = Map("typeName" -> toSQLType(objectType)),
+ sqlState = "0A000")
+
+ checkError(
+ exception = intercept[SparkUnsupportedOperationException] {
+ row.update(0, Integer.valueOf(1))
+ },
+ condition = "UNSUPPORTED_DATATYPE",
+ parameters = Map("typeName" -> toSQLType(objectType)),
+ sqlState = "0A000")
+ } finally {
+ column.close()
+ }
+ }
+
test("RENAME_SRC_PATH_NOT_FOUND: rename the file which source path does not
exist") {
withTempPath { p =>
withSQLConf(
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
