Skip to content

[SPARK-47500][PYTHON][CONNECT][FOLLOWUP] Restore error message for DataFrame.select(None) #46930

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
wants to merge 1 commit into from
Closed

[SPARK-47500][PYTHON][CONNECT][FOLLOWUP] Restore error message for DataFrame.select(None) #46930

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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/sql/connect/dataframe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -223,6 +223,11 @@ def select(self, __cols: Union[List[Column], List[str]]) -> ParentDataFrame:
def select(self, *cols: "ColumnOrName") -> ParentDataFrame: # type: ignore[misc]
if len(cols) == 1 and isinstance(cols[0], list):
cols = cols[0]
if any(not isinstance(c, (str, Column)) for c in cols):
raise PySparkTypeError(
error_class="NOT_LIST_OF_COLUMN_OR_STR",
message_parameters={"arg_name": "columns"},
)
return DataFrame(
plan.Project(self._plan, [F._to_col(c) for c in cols]),
session=self._session,
Expand Down
11 changes: 11 additions & 0 deletions python/pyspark/sql/tests/connect/test_connect_error.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@
from pyspark.errors.exceptions.base import SessionNotSameException
from pyspark.sql.types import Row
from pyspark.testing.connectutils import should_test_connect
from pyspark.errors import PySparkTypeError
from pyspark.errors.exceptions.connect import AnalysisException
from pyspark.sql.tests.connect.test_connect_basic import SparkConnectSQLTestCase

Expand Down Expand Up @@ -214,6 +215,16 @@ def test_column_cannot_be_constructed_from_string(self):
with self.assertRaises(TypeError):
Column("col")

def test_select_none(self):
with self.assertRaises(PySparkTypeError) as e1:
self.connect.range(1).select(None)

self.check_error(
exception=e1.exception,
error_class="NOT_LIST_OF_COLUMN_OR_STR",
message_parameters={"arg_name": "columns"},
)


if __name__ == "__main__":
from pyspark.sql.tests.connect.test_connect_error import * # noqa: F401
Expand Down