def main():
credentials = GoogleCredentials.get_application_default()
http = credentials.authorize(httplib2.Http())
projectId = raw_input('Enter the project ID: ')
datasetId = raw_input('Enter a dataset ID: ')
tableId = raw_input('Enter a table name to load the data to: ')
schema_path = raw_input(
'Enter the path to the schema file for the table: ')
with open(schema_path, 'r') as schema_file:
schema = schema_file.read()
data_path = raw_input('Enter the path to the data file: ')
with open(data_path, 'r') as data_file:
data = data_file.read()
resp, content = make_post(http,
schema,
data,
projectId,
datasetId,
tableId)
if resp.status == 200:
job_resource = json.loads(content)
service = get_service(credentials)
poll_job(service, **job_resource['jobReference'])
print("Success!")
else:
print("Http error code: {}".format(resp.status))
def main():
credentials = GoogleCredentials.get_application_default()
http = credentials.authorize(httplib2.Http())
projectId = raw_input('Enter the project ID: ')
datasetId = raw_input('Enter a dataset ID: ')
tableId = raw_input('Enter a table name to load the data to: ')
schema_path = raw_input(
'Enter the path to the schema file for the table: ')
with open(schema_path, 'r') as schema_file:
schema = schema_file.read()
data_path = raw_input('Enter the path to the data file: ')
with open(data_path, 'r') as data_file:
data = data_file.read()
resp, content = make_post(http, schema, data, projectId, datasetId,
tableId)
if resp.status == 200:
job_resource = json.loads(content)
service = get_service(credentials)
poll_job(service, **job_resource['jobReference'])
print("Success!")
else:
print("Http error code: {}".format(resp.status))
def run(cloud_storage_path, projectId, datasetId, tableId, num_retries,
interval):
bigquery = get_service()
resource = export_table(bigquery, cloud_storage_path, projectId, datasetId,
tableId, num_retries)
poll_job(bigquery, resource['jobReference']['projectId'],
resource['jobReference']['jobId'], interval, num_retries)
def run(project_id, query, timeout, num_retries):
service = get_service()
response = sync_query(service, project_id, query, timeout, num_retries)
for page in paging(service,
service.jobs().getQueryResults,
num_retries=num_retries,
**response['jobReference']):
yield json.dumps(page['rows'])
def run(project_id, dataset_id, table_id, rows, num_retries):
service = get_service()
for row in rows:
response = stream_row_to_bigquery(service,
project_id,
dataset_id,
table_id,
row,
num_retries)
yield json.dumps(response)
def run(cloud_storage_path,
projectId, datasetId, tableId,
num_retries, interval):
bigquery = get_service()
resource = export_table(bigquery, cloud_storage_path,
projectId, datasetId, tableId, num_retries)
poll_job(bigquery,
resource['jobReference']['projectId'],
resource['jobReference']['jobId'],
interval,
num_retries)
def run(source_schema, source_csv,
projectId, datasetId, tableId, interval, num_retries):
service = get_service()
job = load_table(service, source_schema, source_csv,
projectId, datasetId, tableId, num_retries)
poll_job(service,
job['jobReference']['projectId'],
job['jobReference']['jobId'],
interval,
num_retries)
def run(source_schema, source_csv,
projectId, datasetId, tableId, interval, num_retries):
service = get_service()
job = load_table(service, source_schema, source_csv,
projectId, datasetId, tableId, num_retries)
poll_job(service,
job['jobReference']['projectId'],
job['jobReference']['jobId'],
interval,
num_retries)
def run(project_id, query, timeout, num_retries):
service = get_service()
response = sync_query(service,
project_id,
query,
timeout,
num_retries)
for page in paging(service,
service.jobs().getQueryResults,
num_retries=num_retries,
**response['jobReference']):
yield json.dumps(page['rows'])
def run(project_id, query_string, batch, num_retries, interval):
service = get_service()
query_job = async_query(service, project_id, query_string, batch,
num_retries)
poll_job(service, query_job['jobReference']['projectId'],
query_job['jobReference']['jobId'], interval, num_retries)
for page in paging(service,
service.jobs().getQueryResults,
num_retries=num_retries,
**query_job['jobReference']):
yield json.dumps(page['rows'])
def run(project_id, query_string, batch, num_retries, interval):
service = get_service()
query_job = async_query(service,
project_id,
query_string,
batch,
num_retries)
poll_job(service,
query_job['jobReference']['projectId'],
query_job['jobReference']['jobId'],
interval,
num_retries)
for page in paging(service,
service.jobs().getQueryResults,
num_retries=num_retries,
**query_job['jobReference']):
yield json.dumps(page['rows'])
