Align style checks with jwst

.github/CODEOWNERS

@@ -1,3 +1,3 @@
-# automatically requests pull request reviews for files matching the given pattern; the last match takes precendence
+# automatically requests pull request reviews for files matching the given pattern; the last match takes precedence
 
 *       @spacetelescope/stdatamodels-maintainers

.github/workflows/ci.yml

@@ -44,11 +44,13 @@ jobs:
       crds_path: ${{ steps.crds_path.outputs.path }}
       crds_server: ${{ steps.crds_server.outputs.url }}
   check:
-    uses: OpenAstronomy/github-actions-workflows/.github/workflows/tox.yml@8c0fde6f7e926df6ed7057255d29afa9c1ad5320  # v1.16.0
-    with:
-      envs: |
-        - linux: check-style
-        - linux: check-security
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683  # v4.2.2
+    - uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38  # v5.4.0
+      with:
+        python-version: '3.12'
+    - uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd  # v3.0.1
   test:
     uses: OpenAstronomy/github-actions-workflows/.github/workflows/tox.yml@8c0fde6f7e926df6ed7057255d29afa9c1ad5320  # v1.16.0
     needs: [ data ]

.pre-commit-config.yaml

@@ -0,0 +1,35 @@
+exclude: ".*\\.asdf$"
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-ast
+      - id: check-case-conflict
+      - id: check-yaml
+        args: ["--unsafe"]
+      - id: check-toml
+      - id: check-merge-conflict
+      - id: check-symlinks
+      - id: debug-statements
+      - id: detect-private-key
+      # - id: end-of-file-fixer
+      # - id: trailing-whitespace
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: 'v0.9.2'
+    hooks:
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format
+  # - repo: https://github.com/numpy/numpydoc
+  #   rev: v1.8.0
+  #   hooks:
+  #     - id: numpydoc-validation
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.4.0
+    hooks:
+    - id: codespell
+      args: ["--write-changes"]
+      additional_dependencies:
+        - tomli

.ruff.toml

@@ -0,0 +1,70 @@
+extend = "pyproject.toml"
+
+exclude = [
+    ".git",
+    "__pycache__",
+    "docs",
+    ".eggs",
+    "build",
+    "dist",
+    ".tox",
+    ".eggs",
+]
+line-length = 100
+target-version = "py310"
+
+[format]
+quote-style = "double"
+indent-style = "space"
+docstring-code-format = true
+
+[lint]
+select = [
+    "F",      # Pyflakes (part of default flake8)
+    "E",      # pycodestyle (part of default flake8)
+    "W",      # pycodestyle (part of default flake8)
+    #"D",      # docstrings, see also numpydoc pre-commit action
+    "N",      # pep8-naming (naming conventions)
+    "A",      # flake8-builtins (prevent shadowing of builtins)
+    #"ARG",    # flake8-unused-arguments (prevent unused arguments)
+    "B",      # flake8-bugbear (miscellaneous best practices to avoid bugs)
+    "C4",     # flake8-comprehensions (best practices for comprehensions)
+    "ICN",    # flake8-import-conventions (enforce import conventions)
+    "INP",    # flake8-no-pep420 (prevent use of PEP420, i.e. implicit name spaces)
+    "ISC",    # flake8-implicit-str-concat (conventions for concatenating long strings)
+    "LOG",    # flake8-logging
+    "NPY",    # numpy-specific rules
+    "PGH",    # pygrep-hooks (ensure appropriate usage of noqa and type-ignore)
+    "PTH",    # flake8-use-pathlib (enforce using Pathlib instead of os)
+    "S",      # flake8-bandit (security checks)
+    "SLF",    # flake8-self (prevent using private class members outside class)
+    "SLOT",   # flake8-slots (require __slots__ for immutable classes)
+    "T20",    # flake8-print (prevent print statements in code)
+    "TRY",    # tryceratops (best practices for try/except blocks)
+    "UP",     # pyupgrade (simplified syntax allowed by newer Python versions)
+    "YTT",    # flake8-2020 (prevent some specific gotchas from sys.version)
+]
+ignore = [
+    "D100", # missing docstring in public module
+    "E741", # ambiguous variable name (O/0, l/I, etc.)
+    "UP008", # use super() instead of super(class, self). no harm being explicit
+    "UP015", # unnecessary open(file, "r"). no harm being explicit
+    "TRY003", # prevents custom exception messages not defined in exception itself.
+    "ISC001", # single line implicit string concatenation. formatter recommends ignoring this.
+    "PTH123", # use Path.open instead of open
+    "UP038", # isinstance with | instead of ,
+    # longer term fix
+    "S101",  # asserts are used in many non-test places
+    "SLF001",  # private member access, this is overly restrictive
+]
+
+[lint.pydocstyle]
+convention = "numpy"
+
+[lint.flake8-annotations]
+ignore-fully-untyped = true  # Turn of annotation checking for fully untyped code
+
+[lint.per-file-ignores]
+"**/test_*.py" = ["S101", "SLF001", "B011"]
+"tests/**" = ["INP001"]
+"src/stdatamodels/jwst/datamodels/darkMIRI.py" = ["N999"]

changes/383.misc.rst

@@ -0,0 +1 @@
+Apply style checks to code to match jwst.

docs/source/asdf_in_fits.rst

@@ -78,4 +78,4 @@ Finally providing the tree and hdulist to
 
 When read back with :func:`stdatamodels.asdf_in_fits.open` the data for
 ``sci`` and ``dq`` will be read from the HDUList instead of from the
-ASDF data embeded in the HDUList.
+ASDF data embedded in the HDUList.

docs/source/jwst/kwtool/keyword_dictionary.rst

@@ -100,7 +100,7 @@ keyword definitions in the keyword dictionary:
 
 - fits_keyword: the FITS keyword name
 - fits_hdu: the FITS hdu name
-- title: the title of the keyword defintion
+- title: the title of the keyword definition
 - type: one of "float", "integer", "string", "boolean"
 - enum (optional): list of valid values
 

pyproject.toml

@@ -120,6 +120,10 @@ select = [
     "E722",
 ]
 
+[tool.codespell]
+skip = "*.fits, *.asdf, ./build, ./docs/_build, CHANGES.rst, *.schema.yaml"
+ignore-words-list = "indx, delt, Shepard, fo"
+
 [tool.pytest.ini_options]
 minversion = "4.6"
 doctest_plus = true

src/stdatamodels/__init__.py

@@ -2,7 +2,7 @@
 from . import _version
 
 
-__all__ = ['DataModel', '__version__']
+__all__ = ["DataModel", "__version__"]
 
 
 __version__ = _version.version

src/stdatamodels/asdf_in_fits.py

@@ -4,10 +4,7 @@
 from . import fits_support
 
 
-__all__ = [
-    'write',
-    'open'
-]
+__all__ = ["write", "open"]
 
 
 def write(filename, tree, hdulist=None, **kwargs):
@@ -30,7 +27,7 @@ def write(filename, tree, hdulist=None, **kwargs):
     hdulist.writeto(filename, **kwargs)
 
 
-def open(filename_or_hdu, **kwargs):
+def open(filename_or_hdu, **kwargs):  # noqa: A001
     """Read ASDF data embedded in a fits file
 
     Parameters
@@ -46,14 +43,14 @@ def open(filename_or_hdu, **kwargs):
     Returns
     -------
     af : :obj:`asdf.AsdfFile`
-        :obj:`asdf.AsdfFile` created from ASDF data embeded in the opened
+        :obj:`asdf.AsdfFile` created from ASDF data embedded in the opened
         fits file.
     """
 
     is_hdu = isinstance(filename_or_hdu, fits.HDUList)
     hdulist = filename_or_hdu if is_hdu else fits.open(filename_or_hdu)
-    if 'ignore_missing_extensions' not in kwargs:
-        kwargs['ignore_missing_extensions'] = False
+    if "ignore_missing_extensions" not in kwargs:
+        kwargs["ignore_missing_extensions"] = False
     af = fits_support.from_fits_asdf(hdulist, **kwargs)
 
     if is_hdu:
@@ -65,6 +62,7 @@ def wrap_close(af, hdulist):
         def close():
             asdf.AsdfFile.close(af)
             hdulist.close()
+
         return close
 
     af.close = wrap_close(af, hdulist)

src/stdatamodels/basic_utils.py

@@ -33,12 +33,11 @@ def multiple_replace(string, rep_dict):
     If the replacements where chained, the result would have been
     'lamb lamb'
 
-    >>> multiple_replace('button mutton', {'but': 'mut', 'mutton': 'lamb'})
+    >>> multiple_replace("button mutton", {"but": "mut", "mutton": "lamb"})
     'mutton lamb'
 
     """
     pattern = re.compile(
-        "|".join([re.escape(k) for k in sorted(rep_dict, key=len, reverse=True)]),
-        flags=re.DOTALL
+        "|".join([re.escape(k) for k in sorted(rep_dict, key=len, reverse=True)]), flags=re.DOTALL
     )
     return pattern.sub(lambda x: rep_dict[x.group(0)], string)

src/stdatamodels/dqflags.py

@@ -10,6 +10,7 @@
 which provides 32 bits. Bits of an integer are most easily referred to using
 the formula `2**bit_number` where `bit_number` is the 0-index bit of interest.
 """
+
 from astropy.nddata.bitmask import interpret_bit_flags as ap_interpret_bit_flags
 from stdatamodels.basic_utils import multiple_replace
 
@@ -46,10 +47,7 @@ def interpret_bit_flags(bit_flags, flip_bits=None, mnemonic_map=None):
         raise TypeError("`mnemonic_map` is a required argument")
     bit_flags_dm = bit_flags
     if isinstance(bit_flags, str):
-        dm_flags = {
-            key: str(val)
-            for key, val in mnemonic_map.items()
-        }
+        dm_flags = {key: str(val) for key, val in mnemonic_map.items()}
         bit_flags_dm = multiple_replace(bit_flags, dm_flags)
 
     return ap_interpret_bit_flags(bit_flags_dm, flip_bits=flip_bits)
@@ -74,24 +72,26 @@ def dqflags_to_mnemonics(dqflags, mnemonic_map):
 
     Examples
     --------
-    >>> pixel = {'GOOD':             0,      # No bits set, all is good
-    ...          'DO_NOT_USE':       2**0,   # Bad pixel. Do not use
-    ...          'SATURATED':        2**1,   # Pixel saturated during exposure
-    ...          'JUMP_DET':         2**2,   # Jump detected during exposure
-    ...          }
-
-    >>> group = {'GOOD':       pixel['GOOD'],
-    ...          'DO_NOT_USE': pixel['DO_NOT_USE'],
-    ...          'SATURATED':  pixel['SATURATED'],
-    ...          }
+    >>> pixel = {
+    ...     "GOOD": 0,  # No bits set, all is good
+    ...     "DO_NOT_USE": 2**0,  # Bad pixel. Do not use
+    ...     "SATURATED": 2**1,  # Pixel saturated during exposure
+    ...     "JUMP_DET": 2**2,  # Jump detected during exposure
+    ... }
+
+    >>> group = {
+    ...     "GOOD": pixel["GOOD"],
+    ...     "DO_NOT_USE": pixel["DO_NOT_USE"],
+    ...     "SATURATED": pixel["SATURATED"],
+    ... }
 
     >>> dqflags_to_mnemonics(1, pixel)
     {'DO_NOT_USE'}
 
-    >>> dqflags_to_mnemonics(7, pixel)             #doctest: +SKIP
+    >>> dqflags_to_mnemonics(7, pixel)  # doctest: +SKIP
     {'JUMP_DET', 'DO_NOT_USE', 'SATURATED'}
 
-    >>> dqflags_to_mnemonics(7, pixel) == {'JUMP_DET', 'DO_NOT_USE', 'SATURATED'}
+    >>> dqflags_to_mnemonics(7, pixel) == {"JUMP_DET", "DO_NOT_USE", "SATURATED"}
     True
 
     >>> dqflags_to_mnemonics(1, mnemonic_map=pixel)
@@ -100,9 +100,5 @@ def dqflags_to_mnemonics(dqflags, mnemonic_map):
     >>> dqflags_to_mnemonics(1, mnemonic_map=group)
     {'DO_NOT_USE'}
     """
-    mnemonics = {
-        mnemonic
-        for mnemonic, value in mnemonic_map.items()
-        if (dqflags & value)
-    }
+    mnemonics = {mnemonic for mnemonic, value in mnemonic_map.items() if (dqflags & value)}
     return mnemonics

src/stdatamodels/dynamicdq.py

@@ -1,6 +1,7 @@
 import numpy as np
 
 import logging
+
 log = logging.getLogger(__name__)
 log.setLevel(logging.DEBUG)
 log.addHandler(logging.NullHandler())
@@ -32,23 +33,27 @@ def dynamic_mask(input_model, mnemonic_map, inv=False):
 
     dq_table = input_model.dq_def
     # Get the DQ array and the flag definitions
-    if (dq_table is not None and
-        not np.isscalar(dq_table) and
-        len(dq_table.shape) and
-            len(dq_table)):
+    if (
+        (dq_table is not None)
+        and (not np.isscalar(dq_table))
+        and (len(dq_table.shape))
+        and (len(dq_table))
+    ):
         #
         # Make an empty mask
         dqmask = np.zeros(input_model.dq.shape, dtype=input_model.dq.dtype)
         for record in dq_table:
-            bitplane = record['VALUE']
-            dqname = record['NAME'].strip()
+            bitplane = record["VALUE"]
+            dqname = record["NAME"].strip()
 
             # Check that a flag in the 'dq_def' is a valid DQ flag.
             try:
                 standard_bitvalue = mnemonic_map[dqname]
             except KeyError:
-                log.warning('Keyword %s does not correspond to an existing '
-                            'DQ mnemonic, so will be ignored' % (dqname))
+                log.warning(
+                    f"Keyword {dqname} does not correspond to an "
+                    "existing DQ mnemonic, so will be ignored"
+                )
                 continue
 
             if not inv:

src/stdatamodels/filetype.py

@@ -15,24 +15,24 @@ def check(init):
     file_type: a string with the file type ("asdf", "asn", or "fits")
 
     """
-    supported = ('asdf', 'fits', 'json')
+    supported = ("asdf", "fits", "json")
 
     if isinstance(init, str):
-        path, ext = os.path.splitext(init)
-        ext = ext.strip('.')
+        path, ext = os.path.splitext(init)  # noqa: PTH122
+        ext = ext.strip(".")
 
         if not ext:
-            raise ValueError(f'Input file path does not have an extension: {init}')
+            raise ValueError(f"Input file path does not have an extension: {init}")
 
         if ext not in supported:  # Could be the file is zipped; try splitting again
-            path, ext = os.path.splitext(path)
-            ext = ext.strip('.')
+            path, ext = os.path.splitext(path)  # noqa: PTH122
+            ext = ext.strip(".")
 
             if ext not in supported:
-                raise ValueError(f'Unrecognized file type for: {init}')
+                raise ValueError(f"Unrecognized file type for: {init}")
 
-        if ext == 'json':  # Assume json input is an association
-            return 'asn'
+        if ext == "json":  # Assume json input is an association
+            return "asn"
 
         return ext
 
@@ -43,10 +43,10 @@ def check(init):
         if not magic or len(magic) < 5:
             raise ValueError(f"Cannot get file type of {str(init)}")
 
-        if magic == b'#ASDF':
+        if magic == b"#ASDF":
             return "asdf"
 
-        if magic == b'SIMPL':
+        if magic == b"SIMPL":
             return "fits"
 
         return "asn"