Merge pull request #682 from octue/switch-to-ruff-tooling

Switch to ruff developer tooling

Author: thclark

.devcontainer/devcontainer.json

@@ -9,32 +9,19 @@
   // Set *default* container specific settings.json values on container create.
   "settings": {
     "austin.mode": "Wall time",
-    "editor.defaultFormatter": "esbenp.prettier-vscode",
+    "editor.defaultFormatter": "charliermarsh.ruff",
     "editor.formatOnSave": true,
     "jupyter.widgetScriptSources": ["jsdelivr.com", "unpkg.com"],
+    "python.locator": "native",
     "prettier.prettierPath": "/usr/local/prettier",
     "python.formatting.autopep8Path": "/usr/local/py-utils/bin/autopep8",
-    "python.formatting.blackPath": "/usr/local/py-utils/bin/black",
-    "python.formatting.provider": "black",
     "python.formatting.yapfPath": "/usr/local/py-utils/bin/yapf",
     "python.languageServer": "Pylance",
     "python.linting.banditPath": "/usr/local/py-utils/bin/bandit",
     "python.linting.enabled": true,
-    "python.linting.flake8Path": "/usr/local/py-utils/bin/flake8",
     "python.linting.mypyPath": "/usr/local/py-utils/bin/mypy",
     "python.linting.pycodestylePath": "/usr/local/py-utils/bin/pycodestyle",
     "python.linting.pydocstylePath": "/usr/local/py-utils/bin/pydocstyle",
-    // Line length to match black settings
-    // Disabling specific messages:
-    //  - To find the details do: /usr/local/py-utils/bin/pylint --list-msgs
-    //  - Disable missing-module-docstring (C0114) because we don't document modules routinely, just their members
-    //  - Disable invalid-name (C0103) because pylint thinks that eg 'x', 'df', 'np' are invalid due to their lengths
-    "python.linting.pylintArgs": [
-      "--max-line-length=120",
-      "--disable=missing-module-docstring,invalid-name"
-    ],
-    "python.linting.pylintEnabled": true,
-    "python.linting.pylintPath": "/usr/local/py-utils/bin/pylint",
     "python.pythonPath": "/usr/local/bin/python",
     "terminal.integrated.defaultProfile.linux": "zsh"
   },
@@ -51,7 +38,8 @@
     "ms-toolsai.jupyter-keymap",
     "ms-vsliveshare.vsliveshare",
     "p403n1x87.austin-vscode",
-    "ritwickdey.liveserver"
+    "ritwickdey.liveserver",
+    "charliermarsh.ruff"
   ],
 
   // Use 'forwardPorts' to make a list of ports inside the container available locally.

.gitignore

@@ -103,3 +103,6 @@ terraform/gcp-credentials.json
 .terraform
 
 *.jsonl
+
+# Avoid committing ruff cache files
+.ruff_cache

.pre-commit-config.yaml

@@ -12,26 +12,12 @@ repos:
       - id: check-yaml
       - id: check-added-large-files
 
-  - repo: https://github.com/PyCQA/isort
-    rev: 5.10.1
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.6.2
     hooks:
-      - id: isort
-
-  - repo: https://github.com/psf/black
-    rev: 24.4.2
-    hooks:
-      - id: black
-        args: ["--line-length", "120"]
-
-  - repo: https://github.com/pycqa/flake8
-    rev: 6.0.0
-    hooks:
-      - id: flake8
-        language_version: python3
-        additional_dependencies:
-          - "pep8-naming"
-        args:
-          - --ignore-names=setUp,tearDown,setUpClass,tearDownClass,asyncSetUp,asyncTearDown,setUpTestData,failureException,longMessage,maxDiff,startTestRun,stopTestRun
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+      - id: ruff-format
 
   - repo: https://github.com/pre-commit/mirrors-prettier
     rev: v2.7.1
@@ -50,10 +36,10 @@ repos:
         language_version: python3
         additional_dependencies:
           - "poetry==1.2.0b2"
-          - "Sphinx>=4,<5"
+          - "Sphinx>=5,<8"
           - "sphinx-rtd-theme>=1,<2"
           - "sphinx-tabs>=3,<4"
-          - "sphinx-toolbox==3.0.0"
+          - "sphinx-toolbox>=3"
           - "git+https://github.com/octue/octue-sdk-python.git@main"
 
   - repo: https://github.com/windpioneers/pre-commit-hooks

octue/cloud/pub_sub/logging.py

@@ -32,7 +32,7 @@ def __init__(
         retry_count,
         timeout=60,
         *args,
-        **kwargs
+        **kwargs,
     ):
         super().__init__(*args, **kwargs)
         self.question_uuid = question_uuid

octue/diagnostics.py

@@ -176,7 +176,6 @@ def _upload_manifest(self, manifest_type, question_diagnostics_path):
 
         # Upload each dataset and update its path in the manifest.
         for dataset_name, dataset_path in manifest["datasets"].items():
-
             # Handle manifests containing serialised datasets instead of just the datasets' paths. Datasets can be in
             # this state when serialised if they were instantiated using the `files` argument.
             if isinstance(dataset_path, dict):

octue/essentials/monitor_messages.py

@@ -1,6 +1,7 @@
 """A module containing helper functions for sending monitor messages that conform to the Octue essential monitor
 message schema https://jsonschema.registry.octue.com/octue/essential-monitors/0.0.2.json
 """
+
 import logging
 from datetime import datetime, timezone
 

octue/mixins/filterable.py

@@ -156,7 +156,6 @@ def _split_filter_name(self, filter_name):
         *attribute_names, filter_action = filter_name.split("__")
 
         if not attribute_names:
-
             raise exceptions.InvalidInputException(
                 f"Invalid filter name {filter_name!r}. Filter names should be in the form "
                 f"'<attribute_name_0>__<attribute_name_1>__<...>__<filter_kind>' with at least one attribute name "

octue/mixins/hashable.py

@@ -17,7 +17,6 @@
 
 
 class Hashable:
-
     _ATTRIBUTES_TO_HASH = None
     _HASH_TYPE = "CRC32C"
 

octue/resources/datafile.py

@@ -154,7 +154,6 @@ def cloud_path(self, path):
         :return None:
         """
         if path is None:
-
             if not self.exists_locally:
                 raise CloudLocationNotSpecified(
                     "The cloud path cannot be reset because this datafile only exists in the cloud."
@@ -732,7 +731,6 @@ def __exit__(self, *args):
             self._fp.close()
 
         if any(character in self.mode for character in self.MODIFICATION_MODES):
-
             if self.datafile.exists_in_cloud:
                 self.datafile.upload(update_cloud_metadata=self._update_metadata)
 

octue/resources/dataset.py

@@ -300,7 +300,6 @@ def add(self, datafile, path_in_dataset=None):
 
             # Add a cloud datafile to a cloud dataset.
             if datafile.exists_in_cloud:
-
                 if datafile.cloud_path != new_cloud_path and not datafile.cloud_path.startswith(self.path):
                     datafile.upload(new_cloud_path)
 
@@ -350,7 +349,6 @@ def download(self, local_directory=None):
         datafiles_and_paths = []
 
         for file in self.files:
-
             if not file.exists_in_cloud:
                 continue
 

octue/resources/service_backends.py

@@ -5,6 +5,7 @@
 the "oneOf" field of the "backend" key of the children schema in `Twined`, which is located at
 `twined/schema/children_schema.json`.
 """
+
 from abc import ABC
 
 from octue import exceptions

octue/runner.py

@@ -250,7 +250,6 @@ def run(
             analysis_log_level=analysis_log_level,
             extra_log_handlers=extra_log_handlers,
         ):
-
             analysis = Analysis(
                 id=analysis_id,
                 twine=self.twine,

octue/templates/template-fractal/fractal/mandelbrot.py

@@ -26,7 +26,6 @@ def mandelbrot(width, height, x_range, y_range, n_iterations, c=None):
     # Simple loop to render the fractal set. This is not efficient python and would be vectorised in production, but the
     # purpose here is just to provide a simple demo.
     for idx, a in numpy.ndenumerate(x):
-
         # Get default constant c (Mandelbrot sets use spatial coordinates as constants)
         if c is None:
             b = y[idx]