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

Move bigquery 'getting started' sample into github. #78

Merged
merged 2 commits into from
Sep 8, 2015
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
66 changes: 66 additions & 0 deletions bigquery/samples/getting_started.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,66 @@
#!/usr/bin/env python

# Copyright 2015, Google, Inc.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

"""Sample for making BigQuery queries using the python sdk.

This is a command-line script that queries a public shakespeare dataset, and
displays the 10 of Shakespeare's works with the greatest number of distinct
words.
"""
# [START all]
from apiclient.discovery import build
from apiclient.errors import HttpError

from oauth2client.client import GoogleCredentials


def main(project_id):
# [START build_service]
Copy link
Contributor

Choose a reason for hiding this comment

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

Any reason not to use bigquery.samples.utils.get_service()?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Mainly just keeping the sample self-contained.
If I were writing an app, factoring into utils would make sense; but for the purposes of explanation, it's nice to have everything relevant in one place.

# Grab the application's default credentials from the environment.
Copy link
Contributor

Choose a reason for hiding this comment

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

Add a link to the ADC page.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

I feel like that's better left in the doc that uses this sample - urls take up a lot of room, and warrant some text around it explaining why you'd want to go there. eg if I were to add a url in this comment, I'd also want to say something like, "For more information on application default credentials, go to: http...", and that's another two lines of code. If I could just add a footnote to ADC, or link it, that'd work, but since I can't, I'd rather keep the code brief and to the point.

credentials = GoogleCredentials.get_application_default()
# Construct the service object for interacting with the BigQuery API.
bigquery_service = build('bigquery', 'v2', credentials=credentials)
# [END build_service]

try:
# [START run_query]
query_request = bigquery_service.jobs()
query_data = {
'query': ('SELECT TOP(corpus, 10) as title, '
'COUNT(*) as unique_words '
'FROM [publicdata:samples.shakespeare];')
}

query_response = query_request.query(
projectId=project_id,
body=query_data).execute()
# [END run_query]

# [START print_results]
print('Query Results:')
for row in query_response['rows']:
print('\t'.join(field['v'] for field in row['f']))
# [END print_results]

except HttpError as err:
print('Error: {}'.format(err.content))
raise err


if __name__ == '__main__':
# The id of the project to run queries under.
project_id = input("Enter the project ID: ")
main(project_id)
# [END all]
2 changes: 1 addition & 1 deletion bigquery/samples/list_datasets_projects.py
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@ def list_projects(service):

def main(project_id):
credentials = GoogleCredentials.get_application_default()
# Construct the service object for the interacting with the BigQuery API.
# Construct the service object for interacting with the BigQuery API.
service = discovery.build('bigquery', 'v2', credentials=credentials)

list_datasets(service, project_id)
Expand Down
32 changes: 32 additions & 0 deletions bigquery/tests/test_getting_started.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
# Copyright 2015, Google, Inc.
Copy link
Contributor

Choose a reason for hiding this comment

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

Thanks for adding tests. :)

# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import re
import unittest

from bigquery.samples import getting_started

import tests


class TestGettingStarted(tests.CloudBaseTest):
def test_main(self):
with tests.capture_stdout() as mock_stdout:
getting_started.main(self.constants['projectId'])
stdout = mock_stdout.getvalue()
self.assertRegexpMatches(stdout, re.compile(
r'Query Results:.hamlet', re.DOTALL))


if __name__ == '__main__':
unittest.main()