Skip to content

Support ignoreUnknownValues and skipInvalidRows option for insertAll #90

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

Merged
tylertreat merged 2 commits into from
Apr 18, 2016
Merged

Support ignoreUnknownValues and skipInvalidRows option for insertAll #90

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
218b842
Add stream insert options
hagino3000 Apr 14, 2016
5a9290a
Add tests
hagino3000 Apr 18, 2016
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
13 changes: 12 additions & 1 deletion bigquery/client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1137,7 +1137,8 @@ def wait_for_job(self, job, interval=5, timeout=60):

return job_resource

def push_rows(self, dataset, table, rows, insert_id_key=None):
def push_rows(self, dataset, table, rows, insert_id_key=None,
skip_invalid_rows=None, ignore_unknown_values=None):
Copy link
Owner

@tylertreat tylertreat Apr 16, 2016

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Any reason you default these to None rather than False?

Copy link
Contributor Author

@hagino3000 hagino3000 Apr 18, 2016

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

To keep current behavior. Current behavior neither send True nor send False.

"""Upload rows to BigQuery table.

Parameters
Expand All @@ -1150,6 +1151,10 @@ def push_rows(self, dataset, table, rows, insert_id_key=None):
A ``list`` of rows (``dict`` objects) to add to the table
insert_id_key : str, optional
Key for insertId in row
skip_invalid_rows : bool, optional
Insert all valid rows of a request, even if invalid rows exist.
ignore_unknown_values : bool, optional
Accept rows that contain values that do not match the schema.

Returns
-------
Expand All @@ -1173,6 +1178,12 @@ def push_rows(self, dataset, table, rows, insert_id_key=None):
"rows": rows_data
}

if skip_invalid_rows is not None:
data['skipInvalidRows'] = skip_invalid_rows

if ignore_unknown_values is not None:
data['ignoreUnknownValues'] = ignore_unknown_values

try:
response = table_data.insertAll(
projectId=self.project_id,
Expand Down
41 changes: 41 additions & 0 deletions bigquery/tests/test_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2108,6 +2108,47 @@ def test_push_success(self):
self.mock_table_data.insertAll.return_value.execute.assert_has_calls(
execute_calls)

def test_request_data_with_options(self):
"""Ensure that insertAll body has optional property only when
the optional parameter of push_rows passed.
"""
expected_body = self.data.copy()

self.client.push_rows(
self.dataset, self.table, self.rows,
insert_id_key='one')
self.mock_table_data.insertAll.assert_called_with(
projectId=self.project,
datasetId=self.dataset,
tableId=self.table,
body=expected_body)

self.client.push_rows(
self.dataset, self.table, self.rows,
insert_id_key='one',
ignore_unknown_values=False,
skip_invalid_rows=False)
expected_body['ignoreUnknownValues'] = False
expected_body['skipInvalidRows'] = False
self.mock_table_data.insertAll.assert_called_with(
projectId=self.project,
datasetId=self.dataset,
tableId=self.table,
body=expected_body)

self.client.push_rows(
self.dataset, self.table, self.rows,
insert_id_key='one',
ignore_unknown_values=True,
skip_invalid_rows=True)
expected_body['ignoreUnknownValues'] = True
expected_body['skipInvalidRows'] = True
self.mock_table_data.insertAll.assert_called_with(
projectId=self.project,
datasetId=self.dataset,
tableId=self.table,
body=expected_body)


class TestGetAllTables(unittest.TestCase):

Expand Down