Merge pull request #38 from SciCatProject/copier-update

Copier update

.copier-answers.yml

@@ -1,5 +1,5 @@
 # Changes here will be overwritten by Copier; NEVER EDIT MANUALLY
-_commit: d91bf92
+_commit: 1c41c93
 _src_path: gh:scipp/copier_template
 description: A daemon that creates a raw dataset using scicat interface whenever a
     new file is written by a file-writer.

.pre-commit-config.yaml

@@ -13,35 +13,21 @@ repos:
       - id: trailing-whitespace
         args: [ --markdown-linebreak-ext=md ]
         exclude: '\.svg'
-  - repo: https://github.com/pycqa/isort
-    rev: 5.12.0
-    hooks:
-      - id: isort
-        name: isort (python)
-  - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 23.11.0
-    hooks:
-      - id: black
   - repo: https://github.com/kynan/nbstripout
     rev: 0.6.0
     hooks:
       - id: nbstripout
         types: [ "jupyter" ]
         args: [ "--drop-empty-cells",
                 "--extra-keys 'metadata.language_info.version cell.metadata.jp-MarkdownHeadingCollapsed cell.metadata.pycharm'" ]
-  - repo: https://github.com/pycqa/flake8
-    rev: 6.1.0
-    hooks:
-      - id: flake8
-        types: ["python"]
-        additional_dependencies: ["flake8-bugbear==23.9.16"]
-        args: ["--max-line-length=88", "--extend-ignore=E203"]
-  - repo: https://github.com/pycqa/bandit
-    rev: 1.7.5
-    hooks:
-      - id: bandit
-        additional_dependencies: ["bandit[toml]"]
-        args: ["-c", "pyproject.toml"]
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.4.3
+    hooks:
+      - id: ruff
+        args: [ --fix ]
+        types_or: [ python, pyi, jupyter ]
+      - id: ruff-format
+        types_or: [ python, pyi ]
   - repo: https://github.com/codespell-project/codespell
     rev: v2.2.6
     hooks:

pyproject.toml

@@ -67,17 +67,43 @@ filterwarnings = [
   "error",
 ]
 
-[tool.bandit]
-# Excluding tests because bandit doesn't like `assert`.
-exclude_dirs = ["docs/conf.py", "tests"]
+[tool.ruff]
+line-length = 88
+extend-include = ["*.ipynb"]
+extend-exclude = [
+    ".*", "__pycache__", "build", "dist", "install",
+]
+
+[tool.ruff.lint]
+# See https://docs.astral.sh/ruff/rules/
+select = ["B", "C4", "DTZ", "E", "F", "G", "I", "PERF", "PGH", "PT", "PYI", "RUF", "S", "T20", "UP", "W"]
+ignore = [
+    # Conflict with ruff format, see
+    # https://docs.astral.sh/ruff/formatter/#conflicting-lint-rules
+    "COM812", "COM819", "D206", "D300", "E111", "E114", "E117", "ISC001", "ISC002", "Q000", "Q001", "Q002", "Q003", "W191",
+]
+fixable = ["I001", "B010"]
+isort.known-first-party = ["scicat-filewriter-ingest"]
+pydocstyle.convention = "numpy"
 
-[tool.black]
-skip-string-normalization = true
+[tool.ruff.lint.per-file-ignores]
+# those files have an increased risk of relying on import order
+"__init__.py" = ["I"]
+"tests/*" = [
+    "S101",  # asserts are fine in tests
+    "B018",  # 'useless expressions' are ok because some tests just check for exceptions
+]
+"*.ipynb" = [
+    "E501",  # longer lines are sometimes more readable
+    "F403",  # *-imports used with domain types
+    "F405",  # linter may fail to find names because of *-imports
+    "I",  # we don't collect imports at the top
+    "S101",  # asserts are used for demonstration and are safe in notebooks
+    "T201",  # printing is ok for demonstration purposes
+]
 
-[tool.isort]
-skip_gitignore = true
-profile = "black"
-known_first_party = ["scicat-filewriter-ingest"]
+[tool.ruff.format]
+quote-style = "preserve"
 
 [tool.mypy]
 strict = true

requirements/make_base.py

@@ -1,7 +1,6 @@
 import sys
 from argparse import ArgumentParser
 from pathlib import Path
-from typing import List
 
 import tomli
 
@@ -20,7 +19,7 @@
 """
 
 
-def write_dependencies(dependency_name: str, dependencies: List[str]) -> None:
+def write_dependencies(dependency_name: str, dependencies: list[str]) -> None:
     path = Path(f"{dependency_name}.in")
     if path.exists():
         sections = path.read_text().split(CUSTOM_AUTO_SEPARATOR)

src/background-ingestor.py

@@ -2,6 +2,7 @@
 # Copyright (c) 2024 ScicatProject contributors (https://github.com/ScicatProject)
 import json
 import logging
+import pathlib
 from collections.abc import Generator
 from contextlib import contextmanager
 
@@ -56,17 +57,16 @@ def main() -> None:
         logger.info("Nexus file to be ingested : ")
         logger.info(nexus_file)
 
-        done_writing_message_file = (
+        done_writing_message_file = pathlib.Path(
             arg_namespace.arg_namespace.done_writing_message_file
         )
         logger.info("Done writing message file linked to nexus file : ")
         logger.info(done_writing_message_file)
 
         # open and read done writing message input file
-        with open(done_writing_message_file, 'r') as f:
-            done_writing_message = json.load(f)
+        done_writing_message = json.load(done_writing_message_file.open())
+        logger.info(done_writing_message)
 
-        print(done_writing_message)
         # open nexus file
         # nxs = snx.File(nexus_file)
 

src/scicat_configuration.py

@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: BSD-3-Clause
 # Copyright (c) 2024 ScicatProject contributors (https://github.com/ScicatProject)
 import argparse
+from collections.abc import Mapping
 from dataclasses import dataclass
-from typing import Mapping, Optional
 
 
 def build_main_arg_parser() -> argparse.ArgumentParser:
@@ -152,8 +152,8 @@ class RunOptions:
     log_message_prefix: str
     log_level: str
     check_by_job_id: bool
-    system_log_facility: Optional[str] = None
-    pyscicat: Optional[str] = None
+    system_log_facility: str | None = None
+    pyscicat: str | None = None
     graylog: bool = False
 
 
@@ -220,10 +220,10 @@ def build_scicat_config(input_args: argparse.Namespace) -> ScicatConfig:
     ):
         config_dict = json.loads(config_file_path.read_text())
     else:
-        config_dict = dict()
+        config_dict = {}
 
     # Overwrite deep-copied options with command line arguments
-    run_option_dict: dict = copy.deepcopy(config_dict.setdefault("options", dict()))
+    run_option_dict: dict = copy.deepcopy(config_dict.setdefault("options", {}))
     for arg_name, arg_value in vars(input_args).items():
         if arg_value is not None:
             run_option_dict[arg_name] = arg_value
@@ -236,6 +236,6 @@ def build_scicat_config(input_args: argparse.Namespace) -> ScicatConfig:
     return ScicatConfig(
         original_dict=MappingProxyType(config_dict),
         run_options=RunOptions(**run_option_dict),
-        kafka_options=kafkaOptions(**config_dict.setdefault("kafka", dict())),
-        graylog_options=GraylogOptions(**config_dict.setdefault("graylog", dict())),
+        kafka_options=kafkaOptions(**config_dict.setdefault("kafka", {})),
+        graylog_options=GraylogOptions(**config_dict.setdefault("graylog", {})),
     )

src/scicat_ingestor.py

@@ -1,5 +1,16 @@
 # SPDX-License-Identifier: BSD-3-Clause
-# Copyright (c) 2024 ScicatProject contributors (https://github.com/ScicatProject)
+# Copyright (c) 2024 Scicatproject contributors (https://github.com/ScicatProject)
+# ruff: noqa: E402, F401
+
+import importlib.metadata
+
+try:
+    __version__ = importlib.metadata.version(__package__ or __name__)
+except importlib.metadata.PackageNotFoundError:
+    __version__ = "0.0.0"
+
+del importlib
+
 import logging
 from collections.abc import Generator
 from contextlib import contextmanager

src/scicat_kafka.py

@@ -4,14 +4,13 @@
 from collections.abc import Generator
 
 from confluent_kafka import Consumer
+from scicat_configuration import kafkaOptions
 from streaming_data_types import deserialise_wrdn
 from streaming_data_types.finished_writing_wrdn import (
     FILE_IDENTIFIER as WRDN_FILE_IDENTIFIER,
 )
 from streaming_data_types.finished_writing_wrdn import WritingFinished
 
-from scicat_configuration import kafkaOptions
-
 
 def collect_consumer_options(options: kafkaOptions) -> dict:
     """Build a Kafka consumer and configure it according to the ``options``."""
@@ -55,7 +54,7 @@ def build_consumer(kafka_options: kafkaOptions, logger: logging.Logger) -> Consu
         return None
 
     kafka_topics = collect_kafka_topics(kafka_options)
-    logger.info(f"Subscribing to the following Kafka topics: {kafka_topics}")
+    logger.info("Subscribing to the following Kafka topics: %s", kafka_topics)
     consumer.subscribe(kafka_topics)
     return Consumer(consumer_options)
 
@@ -66,7 +65,8 @@ def validate_consumer(consumer: Consumer, logger: logging.Logger) -> bool:
     except Exception as err:
         logger.error(
             "Kafka consumer could not be instantiated. "
-            f"Error message from kafka thread: \n{err}"
+            "Error message from kafka thread: \n%s",
+            err,
         )
         return False
     else:

src/scicat_logging.py

@@ -1,11 +1,10 @@
 # SPDX-License-Identifier: BSD-3-Clause
 # Copyright (c) 2024 ScicatProject contributors (https://github.com/ScicatProject)
+import datetime
 import logging
 import logging.handlers
-from datetime import datetime
 
 import graypy
-
 from scicat_configuration import ScicatConfig
 
 
@@ -24,7 +23,9 @@ def build_logger(config: ScicatConfig) -> logging.Logger:
     if run_options.file_log:
         file_name_components = [run_options.log_filepath_prefix]
         if run_options.file_log_timestamp:
-            file_name_components.append(datetime.now().strftime('%Y%m%d%H%M%S%f'))
+            file_name_components.append(
+                datetime.datetime.now(datetime.UTC).strftime('%Y%m%d%H%M%S%f')
+            )
         file_name_components.append('.log')
 
         file_name = '_'.join(file_name_components)

src/scicat_metadata.py

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: BSD-3-Clause
 # Copyright (c) 2024 ScicatProject contributors (https://github.com/ScicatProject)
+from collections.abc import Callable
 from importlib.metadata import entry_points
-from typing import Callable
 
 
 def load_metadata_extractors(extractor_name: str) -> Callable:

tests/_scicat_ingestor.py

@@ -9,12 +9,11 @@
     from time import sleep
 
     # Run the main function in a subprocess
-    process = subprocess.Popen(
-        [
-            "scicat_ingestor",
-            *(sys.argv[1:] or ["--verbose", "-c", "resources/config.sample.json"]),
-        ]
+    command = (
+        "scicat_ingestor",
+        *(sys.argv[1:] or ["--verbose", "-c", "resources/config.sample.json"]),
     )
+    process = subprocess.Popen(command)  #  noqa: S603
 
     # Send a SIGINT signal to the process after 5 seconds
     sleep(5)

tests/test_logging.py

@@ -1,14 +1,13 @@
 import pathlib
 
 import pytest
-
 from scicat_configuration import GraylogOptions, RunOptions, ScicatConfig, kafkaOptions
 
 
-@pytest.fixture
+@pytest.fixture()
 def scicat_config(tmp_path: pathlib.Path) -> ScicatConfig:
     return ScicatConfig(
-        original_dict=dict(),
+        original_dict={},
         run_options=RunOptions(
             config_file='test',
             verbose=True,

tests/test_metadata_extractor.py

@@ -1,10 +1,9 @@
 import pytest
-
 from scicat_metadata import load_metadata_extractors
 
 
 @pytest.mark.parametrize(
-    ["extractor_name", "expected_result"], [("max", 5), ("min", 1), ("mean", 3)]
+    ("extractor_name", "expected_result"), [("max", 5), ("min", 1), ("mean", 3)]
 )
 def test_metadata_extractor(extractor_name: str, expected_result: int):
     """Test if the metadata extractor can be loaded."""

tests/test_scicat_configuration.py

@@ -3,11 +3,10 @@
 import argparse
 
 import pytest
-
 from scicat_configuration import ScicatConfig
 
 
-@pytest.fixture
+@pytest.fixture()
 def main_arg_parser() -> argparse.ArgumentParser:
     """Return the namespace of the main argument parser."""
     from scicat_configuration import build_main_arg_parser
@@ -34,7 +33,7 @@ def test_scicat_arg_parser_configuration_matches(
     # Parse the configuration file
     assert config_path.exists()
     config_from_file: dict = json.loads(config_path.read_text())
-    main_options: dict = config_from_file.get('options', dict())
+    main_options: dict = config_from_file.get('options', {})
 
     # Check if all keys matches
     all_keys = set(config_from_args.keys()).union(main_options.keys())
@@ -52,7 +51,7 @@ def test_build_scicat_config_default(main_arg_parser: argparse.ArgumentParser) -
     assert scicat_config.run_options.config_file == 'config.20240405.json'
 
 
-@pytest.fixture
+@pytest.fixture()
 def scicat_config(main_arg_parser: argparse.ArgumentParser) -> ScicatConfig:
     from scicat_configuration import build_scicat_config
 

tox.ini

@@ -11,14 +11,14 @@ commands = scicat_ingestor --help  # Minimal test of the script
 
 [testenv:nightly]
 deps = -r requirements/nightly.txt
-commands = pytest
+commands = pytest {posargs}
 
 [testenv:unpinned]
 description = Test with unpinned dependencies, as a user would install now.
 deps =
   -r requirements/basetest.txt
   scicat-filewriter-ingest
-commands = pytest
+commands = pytest {posargs}
 
 [testenv:docs]
 description = invoke sphinx-build to build the HTML docs