Use Ruff (#94)

* Replace linting tools with ruff

* Ruff auto-fixes

* Fix lint errors in app.py and DataDocMetadata.py

* Use 3.11 in workflow

* Fix lint errors in DatasetParser.py

* Add import annotations where needed

* Fix lint errors in ModelBackwardsCompatibility.py

* Fix lint errors in StorageAdapter.py

* Remove unused code

* Fix tests

* Fix lint errors in callbacks package

* Fix lint errors in fields package

* Fix lint errors in components package

* Fix lint errors in tests package

* Tidy final lint errors

* Rename to datadoc_metadata.py

* Rename to dataset_parser.py

* Rename to model_backwards_compatibility.py

* Rename to storage_adapter.py

* Rename to alerts.py

* Fix tests

* Rename to builders.py

* Rename to control_bars.py

* Rename to dataset_tab.py

* Rename to variables_tab.py

* Rename to display_base.py

* Rename to display_dataset.py

* Rename to display_variables.py

* Add VSCode config to gitignore

* Actually rename files

.github/workflows/unit-tests.yml

@@ -20,7 +20,7 @@ jobs:
       - uses: actions/checkout@v2
       - uses: actions/setup-python@v1
         with:
-          python-version: "3.10"
+          python-version: "3.11"
       - uses: Gr1N/setup-poetry@v8
       - uses: actions/cache@v2
         with:
@@ -31,12 +31,9 @@ jobs:
       - name: Install dependencies
         run: |
           poetry install --all-extras
-      - name: Lint with flake8
+      - name: Commit hooks
         run: |
-          # stop the build if there are Python syntax errors or undefined names
-          poetry run pflake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-          # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-          poetry run pflake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+          poetry run pre-commit run --all-files
       - name: Run unit tests
         run: |
           set -o pipefail; poetry run pytest -v --cache-clear --junitxml=pytest.xml --cov-report=term-missing --cov=datadoc | tee pytest-coverage.txt

.gitignore

@@ -1,12 +1,12 @@
 # The file created from the example parquet file
 klargjorte_data/person_data_v1__DOC.json
 
-# This file is changed every time we run it, avoid that being committed
-DataDoc.ipynb
-
 # Jetbrains IDE config
 .idea/
 
+# VSCode config
+.vscode/
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    rev: v4.4.0
     hooks:
       - id: check-ast
       - id: check-added-large-files
@@ -13,30 +13,18 @@ repos:
       - id: end-of-file-fixer
       - id: trailing-whitespace
       - id: mixed-line-ending
-  - repo: local
+  - repo: https://github.com/psf/black
+    rev: 23.7.0
     hooks:
-      - id: autoflake
-        name: autoflake
-        entry: poetry run autoflake -r -i --remove-all-unused-imports --remove-unused-variables
-        language: system
-        types: [python]
-      - id: isort
-        name: isort
-        entry: poetry run isort
-        language: system
-        types: [python]
       - id: black
-        name: black
-        entry: poetry run black
-        language: system
-        types: [python]
-      - id: pyupgrade
-        name: pyupgrade
-        entry: poetry run pyupgrade --py37-plus
-        language: system
-        types: [python]
-      - id: flake8
-        name: flake8
-        entry: poetry run pflake8
-        language: system
-        types: [python]
+        # It is recommended to specify the latest version of Python
+        # supported by your project here, or alternatively use
+        # pre-commit's default_language_version, see
+        # https://pre-commit.com/#top_level-default_language_version
+        language_version: python3.11
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.0.283
+    hooks:
+      - id: ruff
+        args: [ --fix, --exit-non-zero-on-fix ]

.vscode/settings.json

@@ -4,7 +4,7 @@
     "--max-line-length=88",
     "--ignore=E402,F841,F401,E302,E305,W503,E501"
   ],
-  "python.linting.enabled": true,
+  "python.linting.enabled": false,
   "python.linting.pylintEnabled": false,
   "python.linting.mypyEnabled": false,
   "python.languageServer": "Pylance",

SECURITY.md

@@ -1,6 +1,6 @@
 # Security Policy
 
-SSB takes the security of our software products and services seriously, which 
+SSB takes the security of our software products and services seriously, which
 includes all source code repositories managed through our GitHub organization.
 
 We believe that responsible disclosure of security vulnerabilities helps us ensure

datadoc/__init__.py

@@ -1 +1,3 @@
-from datadoc.app import main  # noqa
+"""Datadoc: Document datasets in Statistics Norway."""
+
+from datadoc.app import main

datadoc/app.py

@@ -1,29 +1,35 @@
+"""Top-level entrypoint, configuration and layout for the datadoc app.
+
+Members of this module should not be imported into any sub-modules, this will cause circular imports.
+"""
+from __future__ import annotations
+
 import logging
-import os
+from pathlib import Path
 
 import dash_bootstrap_components as dbc
 from dash import Dash
 from datadoc_model.Enums import SupportedLanguages
 from flask_healthz import healthz
 
-import datadoc.state as state
-from datadoc.backend.DataDocMetadata import DataDocMetadata
+from datadoc import state
+from datadoc.backend.datadoc_metadata import DataDocMetadata
 from datadoc.frontend.callbacks.register_callbacks import register_callbacks
-from datadoc.frontend.components.Alerts import (
+from datadoc.frontend.components.alerts import (
     dataset_validation_error,
     opened_dataset_error,
     opened_dataset_success,
     saved_metadata_success,
     variables_validation_error,
 )
-from datadoc.frontend.components.DatasetTab import get_dataset_tab
-from datadoc.frontend.components.HeaderBars import (
-    get_controls_bar,
-    get_language_dropdown,
+from datadoc.frontend.components.control_bars import (
+    build_controls_bar,
+    build_language_dropdown,
     header,
     progress_bar,
 )
-from datadoc.frontend.components.VariablesTab import get_variables_tab
+from datadoc.frontend.components.dataset_tab import build_dataset_tab
+from datadoc.frontend.components.variables_tab import build_variables_tab
 from datadoc.utils import get_app_version, pick_random_port, running_in_notebook
 
 logger = logging.getLogger(__name__)
@@ -32,18 +38,19 @@
 
 
 def build_app() -> Dash:
+    """Instantiate the Dash app object, define the layout, register callbacks."""
     app = Dash(
         name=NAME,
         title=NAME,
-        assets_folder=f"{os.path.dirname(__file__)}/assets",
+        assets_folder=f"{Path(__file__).parent}/assets",
     )
 
     app.layout = dbc.Container(
         style={"padding": "4px"},
         children=[
             header,
             progress_bar,
-            get_controls_bar(),
+            build_controls_bar(),
             variables_validation_error,
             dataset_validation_error,
             opened_dataset_error,
@@ -56,13 +63,13 @@ def build_app() -> Dash:
                         id="tabs",
                         class_name="ssb-tabs",
                         children=[
-                            get_dataset_tab(),
-                            get_variables_tab(),
+                            build_dataset_tab(),
+                            build_variables_tab(),
                         ],
                     ),
                 ],
             ),
-            get_language_dropdown(),
+            build_language_dropdown(),
         ],
     )
 
@@ -71,9 +78,10 @@ def build_app() -> Dash:
     return app
 
 
-def get_app(dataset_path: str = None) -> Dash:
+def get_app(dataset_path: str | None = None) -> Dash:
+    """Centralize all the ugliness around initializing the app."""
     logging.basicConfig(level=logging.INFO, force=True)
-    logger.info(f"Datadoc version v{get_app_version()}")
+    logger.info("Datadoc version v%s", get_app_version())
     state.current_metadata_language = SupportedLanguages.NORSK_BOKMÅL
     state.metadata = DataDocMetadata(dataset_path)
     app = build_app()
@@ -88,15 +96,16 @@ def get_app(dataset_path: str = None) -> Dash:
     return app
 
 
-def main(dataset_path: str = None):
+def main(dataset_path: str | None = None) -> None:
+    """Entrypoint when running as a script."""
     logging.basicConfig(level=logging.DEBUG, force=True)
-    logger.info(f"Starting app with {dataset_path = }")
+    logger.info("Starting app with dataset_path = %s", dataset_path)
     app = get_app(dataset_path)
     if running_in_notebook():
         logger.info("Running in notebook")
         port = pick_random_port()
         app.run(jupyter_height=1000, port=port)
-        logger.info(f"Server running on port {port}")
+        logger.info("Server running on port %s", port)
     else:
         # Assume running in server mode is better (largely for development purposes)
         logging.basicConfig(level=logging.DEBUG, force=True)