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.

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

feat(gsheets2): retrieve unformatted values instead of formatted ones #214

Merged
merged 7 commits into from
Sep 21, 2020
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
3 changes: 2 additions & 1 deletion doc/connectors/google_sheets_2.md
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@ the url: https://docs.google.com/spreadsheets/d/<spreadsheet_id_is_here>/edit?pr
* `sheet`: str. By default, the extractor returns the first sheet.
* `header_row`: int, default to 0. Row of the header of the spreadsheet

Values are retrieved with the parameter [valueRenderOption](https://developers.google.com/sheets/api/reference/rest/v4/spreadsheets.values/get#body.QUERY_PARAMETERS.value_render_option) set to `UNFORMATTED_VALUE` to escape the rendering based on the locale defined in google sheets.

```coffee
DATA_SOURCES: [
Expand All @@ -45,4 +46,4 @@ DATA_SOURCES: [
,
...
]
```
```
2 changes: 1 addition & 1 deletion setup.py
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ def get_static_file_paths():

setup(
name='toucan_connectors',
version='0.41.3',
version='0.41.4',
description='Toucan Toco Connectors',
long_description=(HERE / 'README.md').read_text(encoding='utf-8'),
long_description_content_type='text/markdown',
Expand Down
14 changes: 12 additions & 2 deletions tests/google_sheets_2/test_google_sheets_2.py
Original file line number Diff line number Diff line change
Expand Up @@ -180,7 +180,7 @@ def test_spreadsheet_without_sheet(mocker, con, ds_without_sheet, fake_kwargs):
"""

def mock_api_responses(uri: str, _token):
if uri.endswith('/Foo'):
if '/Foo' in uri:
return FAKE_SHEET
else:
return FAKE_SHEET_LIST_RESPONSE
Expand All @@ -197,7 +197,7 @@ def mock_api_responses(uri: str, _token):
)
assert (
fetch_mock.call_args_list[1][0][0]
== 'https://sheets.googleapis.com/v4/spreadsheets/1SMnhnmBm-Tup3SfhS03McCf6S4pS2xqjI6CAXSSBpHU/values/Foo'
== 'https://sheets.googleapis.com/v4/spreadsheets/1SMnhnmBm-Tup3SfhS03McCf6S4pS2xqjI6CAXSSBpHU/values/Foo?valueRenderOption=UNFORMATTED_VALUE'
)

assert df.shape == (2, 2)
Expand Down Expand Up @@ -235,3 +235,13 @@ def test_get_status_api_down(mocker, con, fake_kwargs):
mocker.patch.object(GoogleSheets2Connector, '_run_fetch', side_effect=HttpError)

assert con.get_status(**fake_kwargs).status is False


def test_get_decimal_separator(mocker, con, ds, fake_kwargs):
"""
It should returns number data in float type
"""
fake_results = {'metadata': '...', 'values': [['Number'], [1.3], [1.2]]}
mocker.patch.object(GoogleSheets2Connector, '_run_fetch', return_value=fake_results)
df = con.get_df(ds, **fake_kwargs)
assert df.to_dict() == {'Number': {1: 1.3, 2: 1.2}}
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@ def get_form(cls, connector: 'GoogleSheets2Connector', current_config, **kwargs)
with suppress(Exception):
partial_endpoint = current_config['spreadsheet_id']
final_url = f'{connector._baseroute}{partial_endpoint}'
secrets = kwargs.get('secrets')(connector.auth_flow_id)
secrets = kwargs.get('secrets')(auth_flow_id=connector.auth_flow_id)
data = connector._run_fetch(final_url, secrets['access_token'])
available_sheets = [str(x['properties']['title']) for x in data['sheets']]
constraints['sheet'] = strlist_to_enum('sheet', available_sheets)
Expand Down Expand Up @@ -106,9 +106,9 @@ def _retrieve_data(self, data_source: GoogleSheets2DataSource, **kwargs) -> pd.D
data_source.sheet = available_sheets[0]

# https://developers.google.com/sheets/api/samples/reading
read_sheet_endpoint = f'{data_source.spreadsheet_id}/values/{data_source.sheet}'
read_sheet_endpoint = f'{data_source.spreadsheet_id}/values/{data_source.sheet}?valueRenderOption=UNFORMATTED_VALUE'
full_url = f'{self._baseroute}{read_sheet_endpoint}'

# Rajouter le param FORMATTED_VALUE pour le séparateur de décimal dans la Baseroute
data = self._run_fetch(full_url, access_token)['values']
df = pd.DataFrame(data)

Expand All @@ -133,7 +133,7 @@ def get_status(self, **kwargs) -> ConnectorStatus:
If successful, returns a message with the email of the connected user account.
"""
try:
secrets = kwargs.get('secrets')(self.auth_flow_id)
secrets = kwargs.get('secrets')(auth_flow_id=self.auth_flow_id)
access_token = secrets['access_token']
except Exception:
return ConnectorStatus(status=False, error='Credentials are missing')
Expand Down