Skip to content
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

Jump to bottom

fix: throw exception for data type mismatch for load_table_from_dataf… #1824

Closed
wants to merge 1 commit into from
Closed

fix: throw exception for data type mismatch for load_table_from_dataf… #1824

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
14 changes: 9 additions & 5 deletions google/cloud/bigquery/_pandas_helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -302,11 +302,15 @@ def bq_to_arrow_array(series, bq_field):

field_type_upper = bq_field.field_type.upper() if bq_field.field_type else ""

if bq_field.mode.upper() == "REPEATED":
return pyarrow.ListArray.from_pandas(series, type=arrow_type)
if field_type_upper in schema._STRUCT_TYPES:
return pyarrow.StructArray.from_pandas(series, type=arrow_type)
return pyarrow.Array.from_pandas(series, type=arrow_type)
try:
if bq_field.mode.upper() == "REPEATED":
return pyarrow.ListArray.from_pandas(series, type=arrow_type)
if field_type_upper in schema._STRUCT_TYPES:
return pyarrow.StructArray.from_pandas(series, type=arrow_type)

return pyarrow.Array.from_pandas(series, type=arrow_type)
except pyarrow.lib.ArrowInvalid as ae:
raise ValueError(f"{str(ae)} for column {bq_field.name}")


def get_column_or_index(dataframe, name):
Expand Down
24 changes: 24 additions & 0 deletions tests/unit/test_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8963,6 +8963,30 @@ def test_load_table_from_dataframe_w_higher_scale_decimal128_datatype(self):
SchemaField("x", "BIGNUMERIC", "NULLABLE", None),
)

@unittest.skipIf(pandas is None, "Requires `pandas`")
@unittest.skipIf(pyarrow is None, "Requires `pyarrow`")
def test_load_table_from_dataframe_w_datatype_mismatch(self):
from google.cloud.bigquery.schema import SchemaField
from google.cloud.bigquery import job
import re

client = self._make_client()
dataframe = pandas.DataFrame({"x": [1, 2, "three"]})
schema = [SchemaField("x", "INTEGER")]
job_config = job.LoadJobConfig(schema=schema)

get_table_patch = mock.patch(
"google.cloud.bigquery.client.Client.get_table", autospec=True
)
with get_table_patch, pytest.raises(ValueError) as e:
client.load_table_from_dataframe(
dataframe, self.TABLE_REF, location=self.LOCATION, job_config=job_config
)
assert re.match(
r"Could not convert '?three'? with type str: tried to convert to int\d{0,2} for column x",
str(e.value),
)

# With autodetect specified, we pass the value as is. For more info, see
# https://github.com/googleapis/python-bigquery/issues/1228#issuecomment-1910946297
def test_load_table_from_json_basic_use(self):
Expand Down