Add support for pre-commit with mypy and Ruff and start adding type hints

.github/workflows/pytest.yml

@@ -45,12 +45,18 @@ jobs:
           pip install -e .[test]
       - name: Run pip check
         run: pip check
-      - name: Lint with flake8
+      - name: Run pre-commit with mypy
         run: |
-          # stop the build if there are Python syntax errors or undefined names
-          flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-          # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-          flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+          pre-commit install
+          pre-commit run -a
+      # we run pre-commit with ruff and mypy, so this is now redundant
+      # keeping it commented out for now, in case we ever need to come back using it
+      # - name: Lint with flake8
+      #   run: |
+      #     # stop the build if there are Python syntax errors or undefined names
+      #     flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+      #     # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+      #     flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
       - name: Check environment contents
         run: |
           conda list

.gitignore

@@ -8,3 +8,5 @@ __pycache__/
 test-reports/
 <_io.Bytes*>
 pyfive/__pycache__/
+tests/btreev2-generated.hdf5
+tests/__pycache__

.pre-commit-config.yaml

@@ -0,0 +1,49 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+---
+ci:
+  autofix_prs: false
+
+exclude: |
+  (?x)
+  .readthedocs.yaml|
+  codecov.yml|
+  ^.github/|
+  ^doc/
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-ast
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: debug-statements
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+        args: [--markdown-linebreak-ext=md]
+  - repo: https://github.com/adrienverge/yamllint
+    rev: 'v1.37.1'
+    hooks:
+      - id: yamllint
+  # codespell is always iffy; we can turn it on if we want to
+  # - repo: https://github.com/codespell-project/codespell
+  #   rev: 'v2.4.1'
+  #   hooks:
+  #     - id: codespell
+  #       additional_dependencies: [tomli]  # required for Python 3.10
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: "v0.14.9"
+    hooks:
+      - id: ruff-check
+        args: [--fix]
+      - id: ruff-format
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: 'v1.19.1'
+    hooks:
+      - id: mypy
+        additional_dependencies:
+          - 'types-PyYAML'
+          - 'types-requests'
+          - 'numpy'

Changelog.rst

@@ -65,8 +65,8 @@ Version 0.6.0
 
 **2025-09-16**
 
-* Enumeration Support (https://github.com/NCAS-CMS/pyfive/issues/85 by 
-  `Bryan Lawrence <https://github.com/bnlawrence>`_, 
+* Enumeration Support (https://github.com/NCAS-CMS/pyfive/issues/85 by
+  `Bryan Lawrence <https://github.com/bnlawrence>`_,
   `Kai Mühlbauer <https://github.com/kmuehlbauer>`_,
   `Brian Maranville <https://github.com/bmaranville>`_))
 
@@ -208,7 +208,7 @@ Version 0.3.0
 * Support for complex attribute datatypes
   (https://github.com/NCAS-CMS/pyfive/pull/26 by `Jonathan Helmus
   <https://github.com/jjhelmus>`_)
-* Refactor attribute value retrival
+* Refactor attribute value retrieval
   (https://github.com/NCAS-CMS/pyfive/pull/25 by `Jonathan Helmus
   <https://github.com/jjhelmus>`_)
 * Dataset.ndim attribute (https://github.com/NCAS-CMS/pyfive/pull/24
@@ -266,4 +266,3 @@ Version 0.1.0
 **2016-07-26**
 
 * First release by `Jonathan Helmus <https://github.com/jjhelmus>`_
-

codecov.yml

@@ -1,4 +1,4 @@
-codecov: 
+codecov:
   token: bb6507d3-5417-42e2-9faa-6f8bc668bad0
 coverage:
   status:

environment.yml

@@ -5,15 +5,26 @@ channels:
   - nodefaults
 
 dependencies:
+  # core dependencies
   - numpy >=2
   - python >=3.10
-  # testing
+  # testing dependencies
+  - dask
+  - flask
+  - flask-cors
+  - h5netcdf
   - h5py  # link to same hdf5 lib with netcdf4
-  - netcdf4  # has history of broken packages on PyPI
+  - moto
+  - netcdf4 !=1.7.4  # github.com/Unidata/netcdf4-python/issues/1464
+  - pre-commit  # with ruff and mypy
   - pytest
   - pytest-cov
+  - pytest-html
   - pytest-rerunfailures
-  # documentation
+  - pytest-xdist
+  - python-lzf
+  - s3fs >=2025.9.0
+  # documentation dependencies
   - autodocsumm
   - sphinx
   - sphinx_rtd_theme

pyfive/__init__.py

@@ -5,12 +5,18 @@
 """
 
 from pyfive.high_level import File, Group, Dataset
-from pyfive.h5t import check_enum_dtype, check_string_dtype, check_dtype, opaque_dtype, check_opaque_dtype
+from pyfive.h5t import (
+    check_enum_dtype,
+    check_string_dtype,
+    check_dtype,
+    opaque_dtype,
+    check_opaque_dtype,
+)
 from pyfive.h5py import Datatype, Empty
 from importlib.metadata import version
 from pyfive.inspect import p5ncdump
 
-from importlib.metadata import PackageNotFoundError, version
+from importlib.metadata import PackageNotFoundError
 
 try:
     __version__ = version("pyfive")
@@ -22,4 +28,3 @@
     raise PackageNotFoundError(
         msg,
     ) from exc
-