我想做一个简单的脚本来验证GCP数据集中的所有表都有一些数据。 一个数据集可以包含多个表。
1)如何正确调用每个表的断言?
2)我必须为每个数据集创建单独的测试函数。正确吗?
from google.cloud import bigquery
import pytest
CLIENT = bigquery.Client.from_service_account_json('key.json')
def count_verification(dataset):
query = '''SELECT project_id, dataset_id, table_id, row_count
FROM `''' + dataset + '.__TABLES__`;'
query_job = CLIENT.query(query)
return query_job
def test_count_verification(dataset):
for row in count_verification(dataset):
assert row['row_count'] != 0
def test_count_verification_1(dataset_1):
for row in count_verification(dataset_1):
assert row['row_count'] != 0
@pytest.fixture
def dataset():
return 'bigquery-public-data:austin_311'
@pytest.fixture
def dataset_1():
return 'amplified-way-272012:test_dataset'