def test_standalone_sqlalchemy_datasource(test_db_connection_string):
datasource = SqlAlchemyDatasource(
'SqlAlchemy', connection_string=test_db_connection_string, echo=False)
assert datasource.get_available_data_asset_names() == {
"default": ["main.table_1", "main.table_2"]
}
dataset1 = datasource.get_data_asset("main.table_1", "default")
dataset2 = datasource.get_data_asset("main.table_2", "default")
assert isinstance(dataset1, SqlAlchemyDataset)
assert isinstance(dataset2, SqlAlchemyDataset)
def test_sqlalchemy_source_limit(sqlitedb_engine):
df1 = pd.DataFrame({
'col_1': [1, 2, 3, 4, 5],
'col_2': ['a', 'b', 'c', 'd', 'e']
})
df2 = pd.DataFrame({
'col_1': [0, 1, 2, 3, 4],
'col_2': ['b', 'c', 'd', 'e', 'f']
})
df1.to_sql('table_1', con=sqlitedb_engine, index=True)
df2.to_sql('table_2', con=sqlitedb_engine, index=True, schema='main')
datasource = SqlAlchemyDatasource('SqlAlchemy', engine=sqlitedb_engine)
limited_dataset = datasource.get_data_asset("table_1",
"default",
limit=1,
offset=2)
assert isinstance(limited_dataset, SqlAlchemyDataset)
assert limited_dataset._table.name.startswith(
"ge_tmp_") # we have generated a temporary table
assert len(limited_dataset.head(10)) == 1 # and it is only one row long
assert limited_dataset.head(
10)['col_1'][0] == 3 # offset should have been applied
