Enable dependendabot version updates for python code (#1086)

Resolves #814 - Dependabot version updates for python + Initial batch update

.circleci/continue_config.yml

@@ -18,6 +18,7 @@ orbs:
 
 # No windows executor is listed here since windows builds use win/default and modify
 # the Python version through the conda environment.
+# Python 3.10 is pinned to 3.10.6 to work with current version of mypy
 executors:
  docker:
  parameters:
@@ -307,11 +308,11 @@ workflows:
  - e2e_tests:
  matrix:
  parameters:
- python_version: ['3.7', '3.8', '3.9', '3.10']
+ python_version: ['3.7', '3.8', '3.9', '3.10.6'] 
  - win_e2e_tests:
  matrix:
  parameters:
- python_version: ['3.7', '3.8', '3.9', '3.10']
+ python_version: ['3.7', '3.8', '3.9', '3.10.6']
  filters:
  branches:
  only:
@@ -320,11 +321,11 @@ workflows:
  - unit_tests:
  matrix:
  parameters:
- python_version: ['3.7', '3.8', '3.9', '3.10']
+ python_version: ['3.7', '3.8', '3.9', '3.10.6']
  - win_unit_tests:
  matrix:
  parameters:
- python_version: ['3.7', '3.8', '3.9', '3.10']
+ python_version: ['3.7', '3.8', '3.9', '3.10.6']
  filters:
  branches:
  only:
@@ -333,7 +334,7 @@ workflows:
  - lint:
  matrix:
  parameters:
- python_version: ['3.7', '3.8', '3.9', '3.10']
+ python_version: ['3.7', '3.8', '3.9', '3.10.6']
  - all_circleci_checks_succeeded:
  requires:
  - e2e_tests
@@ -359,21 +360,21 @@ workflows:
  - e2e_tests:
  matrix:
  parameters:
- python_version: ['3.7', '3.8', '3.9', '3.10']
+ python_version: ['3.7', '3.8', '3.9', '3.10.6']
  - win_e2e_tests:
  matrix:
  parameters:
- python_version: ['3.7', '3.8', '3.9', '3.10']
+ python_version: ['3.7', '3.8', '3.9', '3.10.6']
  - unit_tests:
  matrix:
  parameters:
- python_version: ['3.7', '3.8', '3.9', '3.10']
+ python_version: ['3.7', '3.8', '3.9', '3.10.6']
  - win_unit_tests:
  matrix:
  parameters:
- python_version: ['3.7', '3.8', '3.9', '3.10']
+ python_version: ['3.7', '3.8', '3.9', '3.10.6']
  - lint:
  matrix:
  parameters:
- python_version: ['3.7', '3.8', '3.9', '3.10']
+ python_version: ['3.7', '3.8', '3.9', '3.10.6']
  - javascript_lint_and_tests

.github/dependabot.yml

@@ -8,11 +8,9 @@ updates:
  - package-ecosystem: "pip" # See documentation for possible values
  directory: "/package" # Location of package manifests
  schedule:
- interval: "daily"
- target-branch: "dependency-update"
+ interval: "weekly"
  ignore:
  - dependency-name: "types-*"
  labels:
- - "python"
+ - "Python"
  - "dependencies"
- open-pull-requests-limit: 50

package/kedro_viz/api/apps.py

@@ -106,6 +106,6 @@ async def index():
 
  @app.get("/api/main", response_class=JSONResponse)
  async def main():
- return json.loads(Path(filepath).read_text())
+ return json.loads(Path(filepath).read_text(encoding="utf8"))
 
  return app

package/kedro_viz/api/graphql/schema.py

@@ -1,6 +1,6 @@
 """`kedro_viz.api.graphql.schema` defines the GraphQL schema: queries, mutations
  and subscriptions.."""
-# pylint: disable=no-self-use,missing-function-docstring,missing-class-docstring
+# pylint: disable=missing-function-docstring,missing-class-docstring
 
 from __future__ import annotations
 

package/kedro_viz/api/rest/router.py

@@ -34,7 +34,7 @@ async def main():
 
 @router.get(
  "/nodes/{node_id}",
- response_model=NodeMetadataAPIResponse, # type: ignore
+ response_model=NodeMetadataAPIResponse,
  response_model_exclude_none=True,
 )
 async def get_single_node_metadata(node_id: str):

package/kedro_viz/integrations/kedro/sqlite_store.py

@@ -1,6 +1,5 @@
 """kedro_viz.intergrations.kedro.sqlite_store is a child of BaseSessionStore
 which stores sessions data in the SQLite database"""
-# pylint: disable=too-many-ancestors
 
 import json
 import logging

package/kedro_viz/integrations/kedro/telemetry.py

@@ -22,7 +22,9 @@ def get_heap_app_id(project_path: Path) -> Optional[str]:
  telemetry_file_path = project_path / ".telemetry"
  if not telemetry_file_path.exists():
  return None
- with open(telemetry_file_path) as telemetry_file:
+ with open(
+ telemetry_file_path, encoding="utf8"
+ ) as telemetry_file: # pylint: disable: unspecified-encoding
  telemetry = yaml.safe_load(telemetry_file)
  if _is_valid_syntax(telemetry) and telemetry["consent"]:
  return _get_heap_app_id()

package/kedro_viz/launchers/jupyter.py

@@ -12,7 +12,7 @@
 
 import IPython
 import requests
-from IPython.core.display import HTML, display
+from IPython.display import HTML, display
 
 from kedro_viz.server import DEFAULT_HOST, DEFAULT_PORT, run_server
 
@@ -73,7 +73,7 @@ def _wait_for(
 def _check_viz_up(host: str, port: int): # pragma: no cover
  url = f"http://{host}:{port}"
  try:
- response = requests.get(url)
+ response = requests.get(url, timeout=10)
  except requests.ConnectionError:
  return False
 

package/kedro_viz/models/flowchart.py

@@ -380,17 +380,21 @@ class TaskNodeMetadata(GraphNodeMetadata):
  """Represent the metadata of a TaskNode"""
 
  # the source code of the node's function
- code: str = field(init=False)
+ code: Optional[str] = field(init=False)
 
  # path to the file where the node is defined
- filepath: str = field(init=False)
+ filepath: Optional[str] = field(init=False)
 
  # parameters of the node, if available
- parameters: Dict = field(init=False)
+ parameters: Optional[Dict] = field(init=False, default=None)
 
  # command to run the pipeline to this node
  run_command: Optional[str] = field(init=False, default=None)
 
+ inputs: List[str] = field(init=False)
+
+ outputs: List[str] = field(init=False)
+
  # the task node to which this metadata belongs
  task_node: InitVar[TaskNode]
 
@@ -468,11 +472,9 @@ def is_plot_node(self):
  Currently it only recognises one underlying dataset as a plot node.
  In the future, we might want to make this generic.
  """
- return (
- self.dataset_type
- == "kedro.extras.datasets.plotly.plotly_dataset.PlotlyDataSet"
- or self.dataset_type
- == "kedro.extras.datasets.plotly.json_dataset.JSONDataSet"
+ return self.dataset_type in (
+ "kedro.extras.datasets.plotly.plotly_dataset.PlotlyDataSet",
+ "kedro.extras.datasets.plotly.json_dataset.JSONDataSet",
  )
 
  def is_image_node(self):
@@ -558,13 +560,13 @@ class DataNodeMetadata(GraphNodeMetadata):
 
  # the optional plot data if the underlying dataset has a plot.
  # currently only applicable for PlotlyDataSet
- plot: Optional[Dict] = field(init=False)
+ plot: Optional[Dict] = field(init=False, default=None)
 
  # the optional image data if the underlying dataset has a image.
  # currently only applicable for matplotlib.MatplotlibWriter
- image: Optional[str] = field(init=False)
+ image: Optional[str] = field(init=False, default=None)
 
- tracking_data: Optional[Dict] = field(init=False)
+ tracking_data: Optional[Dict] = field(init=False, default=None)
 
  # command to run the pipeline to this data node
  run_command: Optional[str] = field(init=False, default=None)
@@ -641,7 +643,7 @@ def load_versioned_tracking_data(
  continue
  else:
  path = version / Path(filepath).name
- with open(path) as fs_file:
+ with open(path, encoding="utf8") as fs_file:
  versions[run_id] = json_stdlib.load(fs_file)
  return versions
 

package/kedro_viz/server.py

@@ -90,11 +90,13 @@ def run_server(
  if save_file:
  response = get_default_response()
  try:
- Path(save_file).write_text(response.json(indent=4, sort_keys=True))
+ Path(save_file).write_text(
+ response.json(indent=4, sort_keys=True), encoding="utf8"
+ )
  except TypeError: # pragma: no cover
  # Keys of incomparable types (e.g. string and int) cannot be sorted.
  Path(save_file).write_text(
- response.json(indent=4, sort_keys=False)
+ response.json(indent=4, sort_keys=False), encoding="utf8"
  ) # pragma: no cover
  app = apps.create_api_app_from_project(path, autoreload)
  else:

package/requirements.txt

@@ -1,12 +1,12 @@
-semver~=2.10 # Needs to be at least 2.10.0 to get VersionInfo.match
+semver~=2.13 # Needs to be at least 2.10.0 to get VersionInfo.match
 kedro>=0.17.0
-ipython>=7.0.0, <8.0
-fastapi>=0.63.0, <0.67.0
-aiofiles==0.6.0
-uvicorn[standard]~=0.17.0
-watchgod~=0.8.0
+ipython>=7.0.0, <9.0
+fastapi>=0.73.0, <0.86.0
+aiofiles==22.1.0
+uvicorn[standard]~=0.18.3
+watchgod~=0.8.2
 plotly>=4.0
 pandas>=0.24
-sqlalchemy~=1.2
+sqlalchemy~=1.4
 strawberry-graphql>=0.99.0, <1.0
 networkx>=1.0

package/test_requirements.txt

@@ -1,21 +1,21 @@
 -r requirements.txt
 kedro[pandas.ParquetDataSet]>=0.17.0 
 kedro-telemetry>=0.1.1 # for testing telemetry integration
-bandit~=1.6.2
-behave>=1.2.6, <2.0
-black~=22.0
-flake8~=3.9.2
-isort~=5.8.0
-matplotlib~=3.3.4
-mypy~=0.930
-psutil==5.8.0 # same as Kedro for now
-pylint~=2.8.2
-pytest~=6.2.0
-pytest-asyncio~=0.17.2
-pytest-cov~=2.11.1
-pytest-mock~=3.6.1
+bandit~=1.7
+behave~=1.2
+black~=22.8
+flake8~=5.0
+isort~=5.10
+matplotlib~=3.5
+mypy~=0.971
+psutil==5.9 # same as Kedro for now
+pylint~=2.15
+pytest~=7.1
+pytest-asyncio~=0.19
+pytest-cov~=3.0
+pytest-mock~=3.8
 sqlalchemy-stubs~=0.4
-trufflehog~=2.1.0
+trufflehog~=2.2
 
 # mypy
 types-aiofiles==0.1.3

package/tests/test_integrations/test_sqlite_store.py

@@ -32,7 +32,7 @@ def db_session_class(store_path):
 class TestSQLiteStore:
  def test_empty(self, store_path):
  sqlite_store = SQLiteStore(store_path, next(session_id()))
- assert sqlite_store == {}
+ assert not sqlite_store
  assert sqlite_store.location == store_path / "session_store.db"
 
  def test_save_single_run(self, store_path, db_session_class):

package/tests/test_models/test_flowchart.py

@@ -418,7 +418,7 @@ def test_plotly_data_node_dataset_not_exist(self):
  plotly_data_node.is_tracking_node.return_value = False
  plotly_data_node.kedro_obj.exists.return_value = False
  plotly_node_metadata = DataNodeMetadata(data_node=plotly_data_node)
- assert not hasattr(plotly_node_metadata, "plot")
+ assert plotly_node_metadata.plot is None
 
  def test_plotly_json_dataset_node_metadata(self):
  mock_plot_data = {
@@ -458,7 +458,7 @@ def test_image_data_node_dataset_not_exist(self):
  image_dataset_node.is_plot_node.return_value = False
  image_dataset_node.kedro_obj.exists.return_value = False
  image_node_metadata = DataNodeMetadata(data_node=image_dataset_node)
- assert not hasattr(image_node_metadata, "image")
+ assert image_node_metadata.image is None
 
  def test_json_data_node_metadata(self):
  mock_json_data = {
@@ -475,7 +475,7 @@ def test_json_data_node_metadata(self):
  json_data_node.kedro_obj.load.return_value = mock_json_data
  json_node_metadata = DataNodeMetadata(data_node=json_data_node)
  assert json_node_metadata.tracking_data == mock_json_data
- assert not hasattr(json_node_metadata, "plot")
+ assert json_node_metadata.plot is None
 
  def test_metrics_data_node_metadata_dataset_not_exist(self):
  metrics_data_node = MagicMock()
@@ -484,8 +484,7 @@ def test_metrics_data_node_metadata_dataset_not_exist(self):
  metrics_data_node.is_metric_node.return_value = True
  metrics_data_node.kedro_obj.exists.return_value = False
  metrics_node_metadata = DataNodeMetadata(data_node=metrics_data_node)
- assert not hasattr(metrics_node_metadata, "metrics")
- assert not hasattr(metrics_node_metadata, "plot")
+ assert metrics_node_metadata.plot is None
 
  def test_data_node_metadata_latest_tracking_data_not_exist(self):
  plotly_data_node = MagicMock()
@@ -494,7 +493,7 @@ def test_data_node_metadata_latest_tracking_data_not_exist(self):
  plotly_data_node.is_tracking_node.return_value = False
  plotly_data_node.kedro_obj.exists.return_value = False
  plotly_node_metadata = DataNodeMetadata(data_node=plotly_data_node)
- assert not hasattr(plotly_node_metadata, "plot")
+ assert plotly_node_metadata.plot is None
 
  @patch("kedro_viz.models.flowchart.DataNodeMetadata.load_versioned_tracking_data")
  def test_tracking_data_node_metadata_versioned_dataset(self, patched_data_loader):
@@ -510,7 +509,7 @@ def test_tracking_data_node_metadata_versioned_dataset(self, patched_data_loader
  tracking_data_node.kedro_obj.load.return_value = mock_metrics_data
  tracking_data_node_metadata = DataNodeMetadata(data_node=tracking_data_node)
  assert tracking_data_node_metadata.tracking_data == mock_metrics_data
- assert hasattr(tracking_data_node_metadata, "plot")
+ assert tracking_data_node_metadata.plot is not None
 
  @patch("kedro_viz.models.flowchart.DataNodeMetadata.load_versioned_tracking_data")
  def test_tracking_data_node_metadata_versioned_dataset_not_exist(
@@ -529,7 +528,7 @@ def test_tracking_data_node_metadata_versioned_dataset_not_exist(
  tracking_data_node.kedro_obj.load.return_value = mock_metrics_data
  tracking_data_node_metadata = DataNodeMetadata(data_node=tracking_data_node)
  assert tracking_data_node_metadata.tracking_data == mock_metrics_data
- assert not hasattr(tracking_data_node_metadata, "plot")
+ assert tracking_data_node_metadata.plot is None
 
  def test_data_node_metadata_create_metrics_plot(self):
  test_versioned_data = {
@@ -566,7 +565,7 @@ def tracking_data_filepath(self, tmp_path):
  for index, directory in enumerate(dir_name):
  filepath = Path(source_dir / directory / filename)
  filepath.parent.mkdir(parents=True, exist_ok=True)
- filepath.write_text(json.dumps(json_content[index]))
+ filepath.write_text(json.dumps(json_content[index]), encoding="utf8")
  return source_dir
 
  @pytest.fixture
@@ -589,7 +588,7 @@ def tracking_data_filepath_reload(self, tmp_path):
  for index, directory in enumerate(dir_name):
  filepath = Path(source_dir / directory / filename)
  filepath.parent.mkdir(parents=True, exist_ok=True)
- filepath.write_text(json.dumps(json_content[index]))
+ filepath.write_text(json.dumps(json_content[index]), encoding="utf8")
  return source_dir
 
  @pytest.fixture
@@ -612,7 +611,7 @@ def tracking_data_filepath_invalid_run_id(self, tmp_path):
  for index, directory in enumerate(dir_name):
  filepath = Path(source_dir / directory / filename)
  filepath.parent.mkdir(parents=True, exist_ok=True)
- filepath.write_text(json.dumps(json_content[index]))
+ filepath.write_text(json.dumps(json_content[index]), encoding="utf8")
  return source_dir
 
  def test_load_metrics_versioned_data(self, tracking_data_filepath):

package/tests/test_server.py

@@ -96,7 +96,7 @@ def test_save_file(self, tmp_path, mocker):
  )
  save_file = tmp_path / "save.json"
  run_server(save_file=save_file)
- with open(save_file, "r") as f:
+ with open(save_file, "r", encoding="utf8") as f:
  assert json.load(f) == {"content": "test"}
 
  @pytest.mark.parametrize(