Merge pull request #257 from nasa/feature/issue-256-fix-pre-commit-du…

…ring-workflows

fix pre-commit during workflows

.pre-commit-config.yaml

@@ -5,7 +5,7 @@ ci:
   autofix_prs: false # Comment "pre-commit.ci autofix" on a PR to trigger
 
 default_language_version:
-  python: python3
+  python: python3.9
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
@@ -16,7 +16,6 @@ repos:
         args: [ '--allow-multiple-documents' ]
       - id: check-toml
       - id: check-json
-        args: ['--autofix', '--no-ensure-ascii', '--no-sort-keys']
       # Check for common mistakes
       - id: check-added-large-files
       - id: check-case-conflict
@@ -29,12 +28,12 @@ repos:
       - id: destroyed-symlinks
       - id: detect-private-key
       - id: end-of-file-fixer
-        exclude: ".ipynb"
+        exclude_types: ["jupyter", "text"]
       - id: mixed-line-ending
       - id: no-commit-to-branch # protects `main` by default
       - id: debug-statements
       - id: trailing-whitespace
-        exclude: ".txt"
+        exclude_types: ["jupyter", "text"]
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.7.3
@@ -43,11 +42,6 @@ repos:
         args: ["--fix", "--exit-non-zero-on-fix"]
       - id: ruff-format
 
-  - repo: https://github.com/psf/black
-    rev: 24.10.0
-    hooks:
-      - id: black-jupyter
-
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.13.0
     hooks:

CHANGELOG.md

@@ -6,6 +6,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [unreleased]
 
+### Removed
+
+- Remove usage of black for code formatting ([#257](https://github.com/nasa/ncompare/pull/257)) ([**@danielfromearth**](https://github.com/danielfromearth))
+
+## [1.10.0] - 2024-07-10
+
 ### Changed
 
 - Group dependabot updates into fewer PRs ([#233](https://github.com/nasa/ncompare/issues/233)) ([**@danielfromearth**](https://github.com/danielfromearth))

CONTRIBUTING.md

@@ -174,8 +174,7 @@ features or old documentation updated for any changed features
 
 ### Python Style Guide
 
-_Ncompare_ follows PEP8 as much as possible. Reference the _ruff_ and
-_black_ configuration sections in [pyproject.toml](pyproject.toml) for specific expectations.
+_Ncompare_ follows PEP8 as much as possible. Reference the _ruff_ configuration section in [pyproject.toml](pyproject.toml) for specific expectations.
 
 ### Documentation
 

README.md

@@ -16,9 +16,6 @@ _____
 <a href="https://pypi.org/project/ncompare" target="_blank">
     <img src="https://img.shields.io/pypi/v/ncompare?color=%2334D058label=pypi%20package" alt="Package version">
 </a>
-<a href="https://github.com/python/black" target="_blank">
-    <img src="https://img.shields.io/badge/code%20style-black-000000.svg" alt="Code style">
-</a>
 <a href="https://mypy-lang.org/" target="_blank">
     <img src="https://www.mypy-lang.org/static/mypy_badge.svg" alt="Mypy checked">
 </a>

ncompare/console.py

@@ -25,6 +25,7 @@
 # See the License for the specific language governing permissions and limitations under the License.
 
 """Command line interface for `ncompare` -- to compare the structure of two NetCDF files."""
+
 import argparse
 import importlib.metadata
 import sys
@@ -34,7 +35,7 @@
 
 from ncompare.core import compare
 
-__version__ = importlib.metadata.version('ncompare')
+__version__ = importlib.metadata.version("ncompare")
 
 
 def _cli(args: Optional[Sequence[str]]) -> argparse.Namespace:
@@ -65,7 +66,10 @@ def _cli(args: Optional[Sequence[str]]) -> argparse.Namespace:
     )
     parser.add_argument("--file-xlsx", help="An Excel file to which the output will be written.")
     parser.add_argument(
-        "--no-color", action="store_true", default=False, help="Turn off all colorized output"
+        "--no-color",
+        action="store_true",
+        default=False,
+        help="Turn off all colorized output",
     )
     parser.add_argument(
         "--show-attributes",
@@ -90,8 +94,8 @@ def _cli(args: Optional[Sequence[str]]) -> argparse.Namespace:
 
     parser.add_argument(
         "--version",
-        action='version',
-        version=f'%(prog)s {__version__}',
+        action="version",
+        version=f"%(prog)s {__version__}",
         default=False,
         help="Show the current version.",
     )
@@ -103,7 +107,7 @@ def main() -> None:  # pragma: no cover
     """Run from the command line."""
     args = _cli(None)
 
-    delattr(args, 'version')
+    delattr(args, "version")
 
     try:
         compare(**vars(args))
@@ -113,5 +117,5 @@ def main() -> None:  # pragma: no cover
     sys.exit(0)  # a clean, no-issue, exit
 
 
-if __name__ == '__main__':  # pragma: no cover
+if __name__ == "__main__":  # pragma: no cover
     main()

ncompare/core.py

@@ -28,10 +28,11 @@
 # pylint: disable=fixme
 
 """Compare the structure of two NetCDF files."""
+
 import random
 import traceback
 from collections import namedtuple
-from collections.abc import Iterable
+from collections.abc import Iterable, Iterator
 from pathlib import Path
 from typing import Optional, Union
 
@@ -46,6 +47,12 @@
 
 VarProperties = namedtuple("VarProperties", "varname, variable, dtype, shape, chunking, attributes")
 
+GroupPair = namedtuple(
+    "GroupPair",
+    "group_a_name group_a group_b_name group_b",
+    defaults=("", None, "", None),
+)
+
 
 def compare(
     nc_a: Union[str, Path],
@@ -195,7 +202,11 @@ def run_through_comparisons(
                     + f"\nChecking multiple random values within specified variable <{comparison_var_name}>:"
                 )
                 compare_multiple_random_values(
-                    out, nc_a, nc_b, groupname=comparison_var_group, varname=comparison_var_name
+                    out,
+                    nc_a,
+                    nc_b,
+                    groupname=comparison_var_group,
+                    varname=comparison_var_name,
                 )
 
             except KeyError:
@@ -250,12 +261,12 @@ def compare_multiple_random_values(
     out.print("Done.", colors=False)
 
 
-def walk_common_groups_tree(  # type:ignore[misc]
+def walk_common_groups_tree(
     top_a_name: str,
     top_a: Union[netCDF4.Dataset, netCDF4.Group],
     top_b_name: str,
     top_b: Union[netCDF4.Dataset, netCDF4.Group],
-) -> tuple[str, netCDF4.Group, str, netCDF4.Group]:
+) -> Iterator[GroupPair]:
     """Yield names and groups from a netCDF4's group tree.
 
     Parameters
@@ -267,25 +278,30 @@ def walk_common_groups_tree(  # type:ignore[misc]
 
     Yields
     ------
-    group A name : str
-    group A object : netCDF4.Group
-    group B name : str
-    group B object : netCDF4.Group
+    tuple
+        group A name : str
+        group A object : netCDF4.Group or None
+        group B name : str
+        group B object : netCDF4.Group or None
     """
-    yield (
-        (
-            top_a_name + "/" + group_a_name if group_a_name else "",
-            top_a[group_a_name] if (group_a_name and (group_a_name in top_a.groups)) else None,
-            top_b_name + "/" + group_b_name if group_b_name else "",
-            top_b[group_b_name] if (group_b_name and (group_b_name in top_b.groups)) else None,
-        )
-        for (_, group_a_name, group_b_name) in common_elements(
-            top_a.groups if top_a is not None else "", top_b.groups if top_b is not None else ""
+    for _, group_a_name, group_b_name in common_elements(
+        top_a.groups if top_a is not None else "",
+        top_b.groups if top_b is not None else "",
+    ):
+        yield GroupPair(
+            group_a_name=top_a_name + "/" + group_a_name if group_a_name else "",
+            group_a=(
+                top_a[group_a_name] if (group_a_name and (group_a_name in top_a.groups)) else None
+            ),
+            group_b_name=top_b_name + "/" + group_b_name if group_b_name else "",
+            group_b=(
+                top_b[group_b_name] if (group_b_name and (group_b_name in top_b.groups)) else None
+            ),
         )
-    )
 
     for _, subgroup_a_name, subgroup_b_name in common_elements(
-        top_a.groups if top_a is not None else "", top_b.groups if top_b is not None else ""
+        top_a.groups if top_a is not None else "",
+        top_b.groups if top_b is not None else "",
     ):
         yield from walk_common_groups_tree(
             top_a_name + "/" + subgroup_a_name if subgroup_a_name else "",
@@ -311,50 +327,57 @@ def compare_two_nc_files(
     show_attributes: bool = False,
 ) -> tuple[int, int, int]:
     """Go through all groups and all variables, and show them side by side - whether they align and where they don't."""
-    out.side_by_side(' ', 'File A', 'File B', force_display_even_if_same=True)
+    out.side_by_side(" ", "File A", "File B", force_display_even_if_same=True)
 
     num_var_diffs = {"left": 0, "right": 0, "both": 0}
     with netCDF4.Dataset(nc_one) as nc_a, netCDF4.Dataset(nc_two) as nc_b:
         out.side_by_side(
-            'All Variables', ' ', ' ', dash_line=False, force_display_even_if_same=True
+            "All Variables", " ", " ", dash_line=False, force_display_even_if_same=True
         )
-        out.side_by_side('-', '-', '-', dash_line=True, force_display_even_if_same=True)
+        out.side_by_side("-", "-", "-", dash_line=True, force_display_even_if_same=True)
 
         group_counter = 0
         _print_group_details_side_by_side(
-            out, nc_a, "/", nc_b, "/", group_counter, num_var_diffs, show_attributes, show_chunks
+            out,
+            nc_a,
+            "/",
+            nc_b,
+            "/",
+            group_counter,
+            num_var_diffs,
+            show_attributes,
+            show_chunks,
         )
         group_counter += 1
 
-        for group_pairs in walk_common_groups_tree("", nc_a, "", nc_b):
-            for group_a_name, group_a, group_b_name, group_b in group_pairs:
-                _print_group_details_side_by_side(
-                    out,
-                    group_a,
-                    group_a_name,
-                    group_b,
-                    group_b_name,
-                    group_counter,
-                    num_var_diffs,
-                    show_attributes,
-                    show_chunks,
-                )
-                group_counter += 1
+        for group_pair in walk_common_groups_tree("", nc_a, "", nc_b):
+            _print_group_details_side_by_side(
+                out,
+                group_pair.group_a,
+                group_pair.group_a_name,
+                group_pair.group_b,
+                group_pair.group_b_name,
+                group_counter,
+                num_var_diffs,
+                show_attributes,
+                show_chunks,
+            )
+            group_counter += 1
 
-    out.side_by_side('-', '-', '-', dash_line=True, force_display_even_if_same=True)
+    out.side_by_side("-", "-", "-", dash_line=True, force_display_even_if_same=True)
     out.side_by_side(
-        'Total number of shared items:',
-        str(num_var_diffs['both']),
-        str(num_var_diffs['both']),
+        "Total number of shared items:",
+        str(num_var_diffs["both"]),
+        str(num_var_diffs["both"]),
         force_display_even_if_same=True,
     )
     out.side_by_side(
-        'Total number of non-shared items:',
-        str(num_var_diffs['left']),
-        str(num_var_diffs['right']),
+        "Total number of non-shared items:",
+        str(num_var_diffs["left"]),
+        str(num_var_diffs["right"]),
         force_display_even_if_same=True,
     )
-    return num_var_diffs['left'], num_var_diffs['right'], num_var_diffs['both']
+    return num_var_diffs["left"], num_var_diffs["right"], num_var_diffs["both"]
 
 
 def _print_group_details_side_by_side(
@@ -369,7 +392,12 @@ def _print_group_details_side_by_side(
     show_chunks: bool,
 ) -> None:
     out.side_by_side(
-        " ", " ", " ", dash_line=False, highlight_diff=False, force_display_even_if_same=True
+        " ",
+        " ",
+        " ",
+        dash_line=False,
+        highlight_diff=False,
+        force_display_even_if_same=True,
     )
     out.side_by_side(
         f"GROUP #{group_counter:02}",
@@ -388,19 +416,19 @@ def _print_group_details_side_by_side(
     if group_b:
         vars_b_sorted = sorted(group_b.variables)
     out.side_by_side(
-        'num variables in group:',
+        "num variables in group:",
         len(vars_a_sorted),
         len(vars_b_sorted),
         highlight_diff=True,
         force_display_even_if_same=True,
     )
-    out.side_by_side('-', '-', '-', dash_line=True, force_display_even_if_same=True)
+    out.side_by_side("-", "-", "-", dash_line=True, force_display_even_if_same=True)
 
     # Count differences between the lists of variables in this group.
     left, right, both = count_diffs(vars_a_sorted, vars_b_sorted)
-    num_var_diffs['left'] += left
-    num_var_diffs['right'] += right
-    num_var_diffs['both'] += both
+    num_var_diffs["left"] += left
+    num_var_diffs["right"] += right
+    num_var_diffs["both"] += both
 
     # Go through each variable in the current group.
     for variable_pair in common_elements(vars_a_sorted, vars_b_sorted):
@@ -473,7 +501,10 @@ def _print_var_properties_side_by_side(
         for attr_a_key, attr_a, attr_b_key, attr_b in get_and_check_variable_attributes(v_a, v_b):
             # Check whether attr_a_key is empty, because it might be if the variable doesn't exist in File A.
             out.side_by_side(
-                f"{attr_a_key if attr_a_key else attr_b_key}:", attr_a, attr_b, highlight_diff=True
+                f"{attr_a_key if attr_a_key else attr_b_key}:",
+                attr_a,
+                attr_b,
+                highlight_diff=True,
             )
 
     # Scale Factor
@@ -483,14 +514,14 @@ def _print_var_properties_side_by_side(
 
 
 def get_and_check_variable_scale_factor(v_a, v_b) -> Union[None, tuple[str, str]]:
-    if getattr(v_a.variable, 'scale_factor', None):
+    if getattr(v_a.variable, "scale_factor", None):
         sf_a = v_a.variable.scale_factor
     else:
-        sf_a = ' '
-    if getattr(v_b.variable, 'scale_factor', None):
+        sf_a = " "
+    if getattr(v_b.variable, "scale_factor", None):
         sf_b = v_b.variable.scale_factor
     else:
-        sf_b = ' '
+        sf_b = " "
     if (sf_a != " ") or (sf_b != " "):
         return str(sf_a), str(sf_b)
     else: