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

Add veneer samples for BigQuery. #444

Merged
merged 1 commit into from
Aug 10, 2016
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
5 changes: 5 additions & 0 deletions bigquery/cloud-client/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
# BigQuery Google Cloud Client Library Samples

<!-- auto-doc-link -->
<!-- end-auto-doc-link -->

83 changes: 83 additions & 0 deletions bigquery/cloud-client/async_query.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,83 @@
#!/usr/bin/env python

# Copyright 2016 Google Inc. All Rights Reserved.
#
# 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.

"""Command-line application to perform asynchronous queries in BigQuery.
Copy link
Contributor

Choose a reason for hiding this comment

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

It would be nice in this application and the sync query one to show an example usage, e.g.:

python sync_query.py "SELECT corpus FROM publicdata.samples.shakespeare` GROUP BY corpus"``

Copy link
Contributor Author

Choose a reason for hiding this comment

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

It would be nice in this application and the sync query one to show an example usage

Done.

For more information, see the README.md under /bigquery.
Example invocation:
$ python async_query.py \
'SELECT corpus FROM `publicdata.samples.shakespeare` GROUP BY corpus'
"""

import argparse
import time
import uuid

from gcloud import bigquery


def async_query(query):
client = bigquery.Client()
query_job = client.run_async_query(str(uuid.uuid4()), query)
query_job.use_legacy_sql = False
query_job.begin()

wait_for_job(query_job)

# Manually construct the QueryResults.
# TODO: The client library will provide a helper method that does this.
# https://github.com/GoogleCloudPlatform/gcloud-python/issues/2083
query_results = bigquery.query.QueryResults('', client)
query_results._properties['jobReference'] = {
'jobId': query_job.name,
'projectId': query_job.project
}

# Drain the query results by requesting a page at a time.
page_token = None
Copy link
Contributor

Choose a reason for hiding this comment

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

A comment explaining that you're draining the query results would be great.


while True:
rows, total_rows, page_token = query_results.fetch_data(
max_results=10,
page_token=page_token)

for row in rows:
print(row)

if not page_token:
break


def wait_for_job(job):
while True:
job.reload() # Refreshes the state via a GET request.
if job.state == 'DONE':
if job.error_result:
raise RuntimeError(job.error_result)
return
time.sleep(1)


if __name__ == '__main__':
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('query', help='BigQuery SQL Query.')

args = parser.parse_args()

async_query(args.query)
27 changes: 27 additions & 0 deletions bigquery/cloud-client/async_query_test.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
# Copyright 2016 Google Inc. All Rights Reserved.
#
# 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.

from async_query import async_query


def test_async_query(cloud_config, capsys):
query = (
'SELECT corpus FROM `publicdata.samples.shakespeare` '
'GROUP BY corpus;')

async_query(query)

out, _ = capsys.readouterr()

assert 'romeoandjuliet' in out
1 change: 1 addition & 0 deletions bigquery/cloud-client/requirements.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
gcloud==0.18.1
66 changes: 66 additions & 0 deletions bigquery/cloud-client/sync_query.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,66 @@
#!/usr/bin/env python

# Copyright 2016 Google Inc. All Rights Reserved.
#
# 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.

"""Command-line application to perform synchronous queries in BigQuery.

For more information, see the README.md under /bigquery.

Example invocation:
$ python sync_query.py \
'SELECT corpus FROM `publicdata.samples.shakespeare` GROUP BY corpus'
"""

import argparse

# [START sync_query]
from gcloud import bigquery


def sync_query(query):
client = bigquery.Client()
query_results = client.run_sync_query(query)

# Use standard SQL syntax for queries.
# See: https://cloud.google.com/bigquery/sql-reference/
query_results.use_legacy_sql = False

query_results.run()

# Drain the query results by requesting a page at a time.
page_token = None

while True:
rows, total_rows, page_token = query_results.fetch_data(
max_results=10,
page_token=page_token)

for row in rows:
print(row)

if not page_token:
break
# [END sync_query]


if __name__ == '__main__':
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('query', help='BigQuery SQL Query.')

args = parser.parse_args()

sync_query(args.query)
27 changes: 27 additions & 0 deletions bigquery/cloud-client/sync_query_test.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
# Copyright 2016 Google Inc. All Rights Reserved.
#
# 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.

from sync_query import sync_query


def test_sync_query(cloud_config, capsys):
query = (
'SELECT corpus FROM `publicdata.samples.shakespeare` '
'GROUP BY corpus;')

sync_query(query)

out, _ = capsys.readouterr()

assert 'romeoandjuliet' in out
4 changes: 2 additions & 2 deletions requirements-dev.txt
Original file line number Diff line number Diff line change
Expand Up @@ -10,8 +10,8 @@ Flask-SQLAlchemy==2.1
Flask==0.11.1
fluent-logger==0.4.3
funcsigs==1.0.2
gcloud==0.17.0
gcloud[grpc]==0.17.0
gcloud==0.18.1
gcloud[grpc]==0.18.1
google-api-python-client==1.5.1
grpc-google-cloud-speech-v1beta1==1.0.1
grpcio==1.0.0rc1
Expand Down