xianzhe-databricks commented on code in PR #52467:
URL: https://github.com/apache/spark/pull/52467#discussion_r2398453183
##########
python/pyspark/sql/tests/test_udf.py:
##########
@@ -1446,6 +1447,95 @@ def my_udf():
self.spark.range(1).select(my_udf().alias("result")).show()
+ def test_udf_binary_type(self):
+ def get_binary_type(x):
+ return type(x).__name__
+
+ binary_udf = udf(get_binary_type, returnType="string")
+
+ df = self.spark.createDataFrame(
+ [Row(b=b"hello"), Row(b=b"world")],
schema=StructType([StructField("b", BinaryType())])
+ )
+
+ with self.sql_conf({"spark.sql.execution.pyspark.binaryAsBytes":
"true"}):
+ result =
df.select(binary_udf(col("b")).alias("type_name")).collect()
+ self.assertEqual(result[0]["type_name"], "bytes")
+ self.assertEqual(result[1]["type_name"], "bytes")
Review Comment:
Ah make huge sense. will do
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
