Skip to content

Allow gzip exported bigquery CSV with -z flag #138

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
merged 1 commit into from
Nov 10, 2015
Merged

Allow gzip exported bigquery CSV with -z flag #138

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
21 changes: 16 additions & 5 deletions bigquery/api/export_data_to_cloud_storage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,8 @@
def export_table(bigquery, cloud_storage_path,
project_id, dataset_id, table_id,
export_format="CSV",
num_retries=5):
num_retries=5,
compression="NONE"):
"""
Starts an export job

Expand All @@ -47,6 +48,8 @@ def export_table(bigquery, cloud_storage_path,
e.g. gs://mybucket/myfolder/
export_format: format to export in;
"CSV", "NEWLINE_DELIMITED_JSON", or "AVRO".
compression: format to compress results with,
"NONE" (default) or "GZIP".

Returns: an extract job resource representing the
job, see https://cloud.google.com/bigquery/docs/reference/v2/jobs
Expand All @@ -66,7 +69,8 @@ def export_table(bigquery, cloud_storage_path,
'tableId': table_id,
},
'destinationUris': [cloud_storage_path],
'destinationFormat': export_format
'destinationFormat': export_format,
'compression': compression
}
}
}
Expand Down Expand Up @@ -101,7 +105,7 @@ def poll_job(bigquery, job):

# [START run]
def main(cloud_storage_path, project_id, dataset_id, table_id,
num_retries, interval, export_format="CSV"):
num_retries, interval, export_format="CSV", compression="NONE"):
# [START build_service]
# Grab the application's default credentials from the environment.
credentials = GoogleCredentials.get_application_default()
Expand All @@ -117,7 +121,8 @@ def main(cloud_storage_path, project_id, dataset_id, table_id,
dataset_id,
table_id,
num_retries=num_retries,
export_format=export_format)
export_format=export_format,
compression=compression)
poll_job(bigquery, job)
# [END run]

Expand All @@ -144,6 +149,11 @@ def main(cloud_storage_path, project_id, dataset_id, table_id,
help='Number of times to retry in case of 500 error.',
type=int,
default=5)
parser.add_argument(
'-z', '--gzip',
help='compress resultset with gzip',
action='store_true',
default=False)

args = parser.parse_args()

Expand All @@ -153,5 +163,6 @@ def main(cloud_storage_path, project_id, dataset_id, table_id,
args.dataset_id,
args.table_id,
args.num_retries,
args.poll_interval)
args.poll_interval,
compression="GZIP" if args.gzip else "NONE")
# [END main]