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

feat(sip-68): Add DatasourceDAO class to manage querying different datasources easier #20030

Merged
merged 4 commits into from
May 13, 2022
Merged
Show file tree
Hide file tree
Changes from 1 commit
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
151 changes: 151 additions & 0 deletions superset/dao/datasource/dao.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,151 @@
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you 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 typing import List, Optional, Set, Union

from flask_babel import _
from sqlalchemy import or_
from sqlalchemy.orm import Session, subqueryload
from sqlalchemy.orm.exc import NoResultFound

from superset.connectors.sqla.models import SqlaTable, Table
from superset.dao.base import BaseDAO
from superset.datasets.commands.exceptions import DatasetNotFoundError
from superset.datasets.models import Dataset
from superset.models.core import Database
from superset.models.sql_lab import Query, SavedQuery

Datasource = Union[Dataset, SqlaTable, Table, Query, SavedQuery]


class DatasourceDAO(BaseDAO):

sources = {
# using table -> SqlaTable for backward compatibility at the moment
"table": SqlaTable,
"query": Query,
"saved_query": SavedQuery,
"sl_dataset": Dataset,
"sl_table": Table,
}

@classmethod
def get_datasource(
cls, datasource_type: str, datasource_id: int, session: Session
) -> Datasource:
if datasource_type not in cls.sources:
raise DatasetNotFoundError()
Copy link
Member

Choose a reason for hiding this comment

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

We should create a custom exception here (DatasourceTypeNotSupportedError, for example).


datasource = (
session.query(cls.sources[datasource_type])
.filter_by(id=datasource_id)
.one_or_none()
)

if not datasource:
raise DatasetNotFoundError()
Copy link
Member

Choose a reason for hiding this comment

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

same thing here re what Beto said above. This could be a missing Table or Query.


return datasource

def get_all_datasources(self, session: Session) -> List[Datasource]:
datasources: List["Datasource"] = []
for source_class in DatasourceDAO.sources.values():
qry = session.query(source_class)
qry = source_class.default_query(qry)
datasources.extend(qry.all())
return datasources
Copy link
Member

Choose a reason for hiding this comment

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

I think we can just limit this to just SqlaTable since no charts or dashboards will be able to be saved with any other datasources


def get_datasource_by_id(self, session: Session, datasource_id: int) -> Datasource:
"""
Find a datasource instance based on the unique id.
:param session: Session to use
:param datasource_id: unique id of datasource
:return: Datasource corresponding to the id
:raises NoResultFound: if no datasource is found corresponding to the id
"""
for datasource_class in DatasourceDAO.sources.values():
try:
return (
session.query(datasource_class)
.filter(datasource_class.id == datasource_id)
.one()
)
except NoResultFound:
# proceed to next datasource type
pass
raise NoResultFound(_("Datasource id not found: %(id)s", id=datasource_id))

def get_datasource_by_name( # pylint: disable=too-many-arguments
self,
session: Session,
datasource_type: str,
datasource_name: str,
schema: str,
database_name: str,
Copy link
Member

Choose a reason for hiding this comment

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

A similar small nit here: in general schema comes after database in our functions/methods (since they are hierarchical), I would swap the order for consistency.

) -> Optional[Datasource]:
datasource_class = DatasourceDAO.sources[datasource_type]
return datasource_class.get_datasource_by_name(
session, datasource_name, schema, database_name
)

def query_datasources_by_permissions( # pylint: disable=invalid-name
self,
session: Session,
database: Database,
permissions: Set[str],
schema_perms: Set[str],
) -> List[Datasource]:
# TODO(bogdan): add unit test
Copy link
Member

@betodealmeida betodealmeida May 11, 2022

Choose a reason for hiding this comment

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

Don't leave TODOs for other people! :)

Suggested change
# TODO(bogdan): add unit test
# TODO(hughhhh): add unit test

Or remove it altogether.

datasource_class = DatasourceDAO.sources[database.type]
return (
session.query(datasource_class)
.filter_by(database_id=database.id)
.filter(
or_(
datasource_class.perm.in_(permissions),
datasource_class.schema_perm.in_(schema_perms),
)
)
.all()
)

def get_eager_datasource(
self, session: Session, datasource_type: str, datasource_id: int
) -> Datasource:
"""Returns datasource with columns and metrics."""
datasource_class = DatasourceDAO.sources[datasource_type]
return (
session.query(datasource_class)
.options(
subqueryload(datasource_class.columns),
subqueryload(datasource_class.metrics),
)
.filter_by(id=datasource_id)
.one()
)

def query_datasources_by_name(
self,
session: Session,
database: Database,
datasource_name: str,
schema: Optional[str] = None,
) -> List[Datasource]:
datasource_class = DatasourceDAO.sources[database.type]
return datasource_class.query_datasources_by_name(
session, database, datasource_name, schema=schema
)
116 changes: 116 additions & 0 deletions tests/unit_tests/dao/datasource_test.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,116 @@
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you 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.

import pytest
from sqlalchemy.orm.session import Session


def create_test_data(session: Session) -> None:
Copy link
Member

Choose a reason for hiding this comment

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

You can also rewrite this as a fixture:

@pytest.fixture
def session_with_data(session: Session) -> Iterator[Session]:
    ...  # code of `create_test_data` here
    yield session

And then in your tests:

def test_get_datasource_sqlatable(app_context: None, session_with_data: Session) -> None:
    ...

But there's no need, a function like this also works fine.

from superset.columns.models import Column
from superset.connectors.sqla.models import SqlaTable, TableColumn
from superset.models.core import Database
from superset.models.sql_lab import Query, SavedQuery

engine = session.get_bind()
SqlaTable.metadata.create_all(engine) # pylint: disable=no-member

db = Database(database_name="my_database", sqlalchemy_uri="sqlite://")

columns = [
TableColumn(column_name="a", type="INTEGER"),
]

sqla_table = SqlaTable(
table_name="my_sqla_table",
columns=columns,
metrics=[],
database=db,
)

query_obj = Query(
client_id="foo",
database=db,
tab_name="test_tab",
sql_editor_id="test_editor_id",
sql="select * from bar",
select_sql="select * from bar",
executed_sql="select * from bar",
limit=100,
select_as_cta=False,
rows=100,
error_message="none",
results_key="abc",
)

saved_query = SavedQuery(database=db, sql="select * from foo")

session.add(saved_query)
session.add(query_obj)
session.add(db)
session.add(sqla_table)
session.flush()


def test_get_datasource_sqlatable(app_context: None, session: Session) -> None:
from superset.connectors.sqla.models import SqlaTable
from superset.dao.datasource.dao import DatasourceDAO

create_test_data(session)

result = DatasourceDAO.get_datasource(
datasource_type="table", datasource_id=1, session=session
)

assert 1 == result.id
assert "my_sqla_table" == result.table_name
assert isinstance(result, SqlaTable)


def test_get_datasource_query(app_context: None, session: Session) -> None:
from superset.dao.datasource.dao import DatasourceDAO
from superset.models.sql_lab import Query

create_test_data(session)

result = DatasourceDAO.get_datasource(
datasource_type="query", datasource_id=1, session=session
)

assert result.id == 1
assert isinstance(result, Query)


def test_get_datasource_saved_query(app_context: None, session: Session) -> None:
from superset.dao.datasource.dao import DatasourceDAO
from superset.models.sql_lab import SavedQuery

create_test_data(session)

result = DatasourceDAO.get_datasource(
datasource_type="saved_query", datasource_id=1, session=session
)

assert result.id == 1
assert isinstance(result, SavedQuery)


def test_get_datasource_sl_table(app_context: None, session: Session) -> None:
pass
Copy link
Member

Choose a reason for hiding this comment

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

Is there a reason these are just pass?

Copy link
Member Author

Choose a reason for hiding this comment

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

I'm currently working on these test now and will push them up soon



def test_get_datasource_sl_dataset(app_context: None, session: Session) -> None:
pass