Skip to content

[SPARK-55525][PYTHON] Fix UDTF_ARROW_TYPE_CONVERSION_ERROR with undefined error message parameter #54318

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
allisonwang-db wants to merge 5 commits into from
Closed

[SPARK-55525][PYTHON] Fix UDTF_ARROW_TYPE_CONVERSION_ERROR with undefined error message parameter #54318

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
1ad6cfd
fix
allisonwang-db Feb 13, 2026
c0999a5
fix tests
allisonwang-db Feb 13, 2026
80a1bcd
fix tests
allisonwang-db Feb 18, 2026
0e0cc5c
fix
allisonwang-db Feb 19, 2026
54fd569
lint
allisonwang-db Feb 19, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions python/pyspark/errors/error-conditions.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1253,6 +1253,11 @@
"Return type of the user-defined function should be <expected>, but is <actual>."
]
},
"UDTF_ARROW_DATA_CONVERSION_ERROR": {
"message": [
"Cannot convert UDTF output to Arrow. Data: <data>. Schema: <schema>. Arrow Schema: <arrow_schema>."
]
},
"UDTF_ARROW_TYPE_CAST_ERROR": {
"message": [
"Cannot convert the output value of the column '<col_name>' with type '<col_type>' to the specified return type of the column: '<arrow_type>'. Please check if the data types match and try again."
Expand Down
17 changes: 17 additions & 0 deletions python/pyspark/sql/tests/arrow/test_arrow_udtf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,23 @@

@unittest.skipIf(not have_pyarrow, pyarrow_requirement_message)
class ArrowUDTFTestsMixin:
def test_arrow_udtf_data_conversion_error(self):
from pyspark.sql.functions import udtf

@udtf(returnType="x int, y int")
class DataConversionErrorUDTF:
def eval(self):
# Return a non-tuple value when multiple return values are expected.
# This will cause LocalDataToArrowConversion.convert to fail with TypeError (len() on int),
# which should be wrapped in UDTF_ARROW_DATA_CONVERSION_ERROR.
yield 1

# Enable Arrow optimization for regular UDTFs
with self.sql_conf({"spark.sql.execution.pythonUDTF.arrow.enabled": "true"}):
with self.assertRaisesRegex(PythonException, "UDTF_ARROW_DATA_CONVERSION_ERROR"):
result_df = DataConversionErrorUDTF()
result_df.collect()

def test_arrow_udtf_zero_args(self):
@arrow_udtf(returnType="id int, value string")
class TestUDTF:
Expand Down
16 changes: 8 additions & 8 deletions python/pyspark/sql/tests/test_udtf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3745,7 +3745,7 @@ class TestUDTF:
def eval(self):
yield 1,

err = "UDTF_ARROW_TYPE_CONVERSION_ERROR"
err = "UDTF_ARROW_DATA_CONVERSION_ERROR"

for ret_type, expected in [
("x: boolean", err),
Expand All @@ -3772,7 +3772,7 @@ class TestUDTF:
def eval(self):
yield "1",

err = "UDTF_ARROW_TYPE_CONVERSION_ERROR"
err = "UDTF_ARROW_DATA_CONVERSION_ERROR"

for ret_type, expected in [
("x: boolean", err),
Expand Down Expand Up @@ -3801,7 +3801,7 @@ class TestUDTF:
def eval(self):
yield "hello",

err = "UDTF_ARROW_TYPE_CONVERSION_ERROR"
err = "UDTF_ARROW_DATA_CONVERSION_ERROR"
for ret_type, expected in [
("x: boolean", err),
("x: tinyint", err),
Expand Down Expand Up @@ -3829,7 +3829,7 @@ class TestUDTF:
def eval(self):
yield [0, 1.1, 2],

err = "UDTF_ARROW_TYPE_CONVERSION_ERROR"
err = "UDTF_ARROW_DATA_CONVERSION_ERROR"
for ret_type, expected in [
("x: boolean", err),
("x: tinyint", err),
Expand Down Expand Up @@ -3861,7 +3861,7 @@ class TestUDTF:
def eval(self):
yield {"a": 0, "b": 1.1, "c": 2},

err = "UDTF_ARROW_TYPE_CONVERSION_ERROR"
err = "UDTF_ARROW_DATA_CONVERSION_ERROR"
for ret_type, expected in [
("x: boolean", err),
("x: tinyint", err),
Expand Down Expand Up @@ -3892,7 +3892,7 @@ class TestUDTF:
def eval(self):
yield {"a": 0, "b": 1.1, "c": 2},

err = "UDTF_ARROW_TYPE_CONVERSION_ERROR"
err = "UDTF_ARROW_DATA_CONVERSION_ERROR"
for ret_type, expected in [
("x: boolean", err),
("x: tinyint", err),
Expand Down Expand Up @@ -3922,7 +3922,7 @@ class TestUDTF:
def eval(self):
yield Row(a=0, b=1.1, c=2),

err = "UDTF_ARROW_TYPE_CONVERSION_ERROR"
err = "UDTF_ARROW_DATA_CONVERSION_ERROR"
for ret_type, expected in [
("x: boolean", err),
("x: tinyint", err),
Expand Down Expand Up @@ -3958,7 +3958,7 @@ def eval(self):
"x: array<int>",
]:
with self.subTest(ret_type=ret_type):
with self.assertRaisesRegex(PythonException, "UDTF_ARROW_TYPE_CONVERSION_ERROR"):
with self.assertRaisesRegex(PythonException, "UDTF_ARROW_DATA_CONVERSION_ERROR"):
udtf(TestUDTF, returnType=ret_type)().collect()

def test_decimal_round(self):
Expand Down
2 changes: 1 addition & 1 deletion python/pyspark/worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2343,7 +2343,7 @@ def convert_to_arrow(data: Iterable):

def raise_conversion_error(original_exception):
raise PySparkRuntimeError(
errorClass="UDTF_ARROW_TYPE_CONVERSION_ERROR",
errorClass="UDTF_ARROW_DATA_CONVERSION_ERROR",
messageParameters={
"data": str(data),
"schema": return_type.simpleString(),
Expand Down