Add git pre-commit hooks

.github/workflows/test_and_build.yml

@@ -54,7 +54,8 @@ jobs:
           activate-environment: graphblas
       - name: Update env
         run: |
-          conda install -c conda-forge pytest coverage 'black>=20.8b1' flake8 coveralls pytest-randomly
+          conda install -c conda-forge pytest coverage 'black>=20.8b1' flake8 \
+          coveralls pytest-randomly flake8-comprehensions flake8-bugbear
       - name: Style Checks
         run: |
           flake8

.pre-commit-config.yaml

@@ -0,0 +1,56 @@
+# https://pre-commit.com/
+#
+# Before first use: `pre-commit install`
+# To run: `pre-commit run --all-files`
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.2.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-yaml
+      - id: debug-statements
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+      - id: trailing-whitespace
+  - repo: https://github.com/myint/autoflake
+    rev: v1.4
+    hooks:
+      - id: autoflake
+        args: [--in-place]
+  - repo: https://github.com/pycqa/isort
+    rev: 5.10.1
+    hooks:
+      - id: isort
+        language_version: python3
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v2.32.0
+    hooks:
+      - id: pyupgrade
+        args: [--py38-plus]
+  - repo: https://github.com/psf/black
+    rev: 22.3.0
+    hooks:
+      - id: black
+        language_version: python3
+        args: [--target-version=py38]
+  - repo: https://github.com/PyCQA/flake8
+    rev: 4.0.1
+    hooks:
+      - id: flake8
+        additional_dependencies: &flake8_dependencies
+        - flake8==4.0.1
+        - flake8-comprehensions==3.8.0
+        - flake8-bugbear==22.3.23
+  - repo: https://github.com/asottile/yesqa
+    rev: v1.3.0
+    hooks:
+      - id: yesqa
+        additional_dependencies: *flake8_dependencies
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.1.0
+    hooks:
+      - id: codespell
+        types_or: [python, rst, markdown]
+        files: ^(graphblas|docs)/
+        args: ["--ignore-words-list=coo,ba"]
+# Maybe: black-jupyter, blacken-docs, blackdoc mypy, velin

README.md

@@ -6,7 +6,6 @@
 [![Tests](https://github.com/metagraph-dev/python-graphblas/workflows/Tests/badge.svg?branch=main)](https://github.com/metagraph-dev/python-graphblas/actions)
 [![Docs](https://readthedocs.org/projects/python-graphblas/badge/?version=latest)](https://python-graphblas.readthedocs.io/en/latest/)
 [![Coverage](https://coveralls.io/repos/metagraph-dev/python-graphblas/badge.svg?branch=main)](https://coveralls.io/r/metagraph-dev/python-graphblas)
-[![Code style](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/metagraph-dev/python-graphblas/HEAD?filepath=notebooks%2FIntro%20to%20GraphBLAS%20%2B%20SSSP%20example.ipynb)
 
 Python wrapper around GraphBLAS

graphblas/__init__.py

@@ -4,7 +4,7 @@
 from importlib.abc import MetaPathFinder as _MetaPathFinder
 
 from . import mask  # noqa
-from ._version import get_versions  # noqa
+from ._version import get_versions
 
 
 class replace:
@@ -110,7 +110,7 @@ def init(backend="suitesparse", blocking=False):
 def _init(backend_arg, blocking, automatic=False):
     global _init_params, backend, lib, ffi
 
-    passed_params = dict(backend=backend_arg, blocking=blocking, automatic=automatic)
+    passed_params = {"backend": backend_arg, "blocking": blocking, "automatic": automatic}
     if _init_params is not None:
         if blocking is None:
             passed_params["blocking"] = _init_params["blocking"]

graphblas/_ss/matrix.py

@@ -3834,6 +3834,7 @@ def compactify_rowwise(
             - smallest : take the smallest values (if tied, may take any)
             - largest : take the largest values (if tied, may take any)
             - random : take values randomly with equal probability and without replacement
+              Chosen values may not be ordered randomly
         reverse : bool, default False
             Reverse the values in each row when True
         asindex : bool, default False
@@ -3867,6 +3868,7 @@ def compactify_columnwise(
             - smallest : take the smallest values (if tied, may take any)
             - largest : take the largest values (if tied, may take any)
             - random : take values randomly with equal probability and without replacement
+              Chosen values may not be ordered randomly
         reverse : bool, default False
             Reverse the values in each column when True
         asindex : bool, default False

graphblas/_ss/vector.py

@@ -1370,6 +1370,7 @@ def selectk(self, how, k, *, name=None):
         ----------
         how : str
             - "random": choose k elements with equal probability
+               Chosen values may not be ordered randomly
             - "first": choose the first k elements
             - "last": choose the last k elements
             - "largest": choose the k largest elements.  If tied, any may be chosen.

graphblas/_version.py

@@ -116,7 +116,7 @@ def versions_from_parentdir(parentdir_prefix, root, verbose):
     """
     rootdirs = []
 
-    for i in range(3):
+    for _ in range(3):
         dirname = os.path.basename(root)
         if dirname.startswith(parentdir_prefix):
             return {
@@ -284,7 +284,7 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
         # TAG-NUM-gHEX
         mo = re.search(r"^(.+)-(\d+)-g([0-9a-f]+)$", git_describe)
         if not mo:
-            # unparseable. Maybe git-describe is misbehaving?
+            # unparsable. Maybe git-describe is misbehaving?
             pieces["error"] = "unable to parse git-describe output: '%s'" % describe_out
             return pieces
 
@@ -511,7 +511,7 @@ def get_versions():
         # versionfile_source is the relative path from the top of the source
         # tree (where the .git directory might live) to this file. Invert
         # this to find the root from __file__.
-        for i in cfg.versionfile_source.split("/"):
+        for _ in cfg.versionfile_source.split("/"):
             root = os.path.dirname(root)
     except NameError:
         return {

graphblas/descriptor.py

@@ -73,7 +73,7 @@ def lookup(
     mask_complement=False,
     mask_structure=False,
     transpose_first=False,
-    transpose_second=False
+    transpose_second=False,
 ):
     key = (
         output_replace,

graphblas/io.py

@@ -159,8 +159,8 @@ def mmread(source, *, dup_op=None, name=None):
     https://math.nist.gov/MatrixMarket/formats.html
     """
     try:
-        from scipy.io import mmread  # noqa
-        from scipy.sparse import coo_matrix  # noqa
+        from scipy.io import mmread
+        from scipy.sparse import coo_matrix
     except ImportError:  # pragma: no cover
         raise ImportError("scipy is required to read Matrix Market files") from None
     array = mmread(source)
@@ -180,7 +180,7 @@ def mmwrite(target, matrix, *, comment="", field=None, precision=None, symmetry=
     https://docs.scipy.org/doc/scipy/reference/generated/scipy.io.mmwrite.html
     """
     try:
-        from scipy.io import mmwrite  # noqa
+        from scipy.io import mmwrite
     except ImportError:  # pragma: no cover
         raise ImportError("scipy is required to write Matrix Market files") from None
 

graphblas/operator.py

@@ -892,7 +892,7 @@ def _build(cls, name, func, *, anonymous=False, is_udt=False):
         return_types = {}
         nt = numba.types
         if not is_udt:
-            for type_, sample_val in _sample_values.items():
+            for type_ in _sample_values:
                 sig = (type_.numba_type,)
                 try:
                     unary_udf.compile(sig)
@@ -1391,7 +1391,7 @@ def _build(cls, name, func, *, is_udt=False, anonymous=False):
         return_types = {}
         nt = numba.types
         if not is_udt:
-            for type_, sample_val in _sample_values.items():
+            for type_ in _sample_values:
                 sig = (type_.numba_type, type_.numba_type)
                 try:
                     binary_udf.compile(sig)

graphblas/scalar.py

@@ -29,7 +29,7 @@ def _scalar_index(name):
 class Scalar(BaseType):
     """
     GraphBLAS Scalar
-    Pseudo-object for GraphBLAS functions which accumlate into a scalar type
+    Pseudo-object for GraphBLAS functions which accumulate into a scalar type
     """
 
     __slots__ = "_empty", "_is_cscalar"

graphblas/tests/test_dtype.py

@@ -110,9 +110,9 @@ def test_unify_dtypes():
 
 def test_dtype_bad_comparison():
     with pytest.raises(TypeError):
-        dtypes.BOOL == object()
+        assert dtypes.BOOL == object()
     with pytest.raises(TypeError):
-        object() != dtypes.BOOL
+        assert object() != dtypes.BOOL
 
 
 def test_dtypes_match_numpy():
@@ -137,7 +137,7 @@ def test_pickle():
             assert val.np_type == val2.np_type
             assert val.name == val2.name
         else:
-            val == val2
+            assert val == val2
     s = pickle.dumps(dtypes._INDEX)
     val2 = pickle.loads(s)
     assert dtypes._INDEX == val2
@@ -170,7 +170,7 @@ def test_lt_dtypes():
     assert sorted(all_dtypes) == expected
     assert dtypes.BOOL < "FP32"
     with pytest.raises(TypeError):
-        dtypes.BOOL < 5
+        assert dtypes.BOOL < 5
 
 
 def test_bad_register():

graphblas/tests/test_formatting.py

@@ -3247,7 +3247,7 @@ def test_mxv_repr_html(A, v):
 
 @pytest.mark.skipif("not pd")
 def test_matrix_reduce_columns_repr_html(A):
-    # This is implmeneted using the transpose of A, so make sure we're oriented correctly!
+    # This is implemented using the transpose of A, so make sure we're oriented correctly!
     html_printer(A.reduce_columnwise(), "A.reduce_columnwise()")
     assert repr_html(A.reduce_columnwise()) == (
         '<div><details class="gb-expr-details"><summary class="gb-expr-summary"><b><tt>gb.VectorExpression:</tt></b><div>\n'

graphblas/tests/test_matrix.py

@@ -1784,9 +1784,9 @@ def test_import_export(A, do_iso, methods):
             assert B5b.ss.is_iso is do_iso
         else:
             # B5b == [A, A]
-            B5b.nvals == 2 * A.nvals
-            B5b.nrows == A.nrows
-            B5b.ncols == 2 * A.ncols
+            assert B5b.nvals == 2 * A.nvals
+            assert B5b.nrows == 2 * A.nrows
+            assert B5b.ncols == A.ncols
     else:
         A5.ss.pack_any(**d)
         assert A5.isequal(A)
@@ -2201,26 +2201,26 @@ def test_no_bool_or_eq(A):
     with pytest.raises(TypeError, match="not defined"):
         bool(A)
     # with pytest.raises(TypeError, match="not defined"):
-    A == A
+    assert (A == A) is not None
     with pytest.raises(TypeError, match="not defined"):
         bool(A.S)
     with pytest.raises(TypeError, match="not defined"):
-        A.S == A.S
+        assert A.S == A.S
     expr = A.ewise_mult(A)
     with pytest.raises(TypeError, match="not defined"):
         bool(expr)
     with pytest.raises(TypeError, match="not enabled"):
-        expr == expr
+        assert expr == expr
     assigner = A[1, 2]()
     with pytest.raises(TypeError, match="not defined"):
         bool(assigner)
     with pytest.raises(TypeError, match="not defined"):
-        assigner == assigner
+        assert assigner == assigner
     updater = A()
     with pytest.raises(TypeError, match="not defined"):
         bool(updater)
     with pytest.raises(TypeError, match="not defined"):
-        updater == updater
+        assert updater == updater
 
 
 @autocompute
@@ -2241,7 +2241,7 @@ def test_bool_eq_on_scalar_expressions(A):
 
     expr = A[0, [1, 1]]
     # with pytest.raises(TypeError, match="not defined"):
-    expr == expr  # Now okay
+    assert (expr == expr) is not None  # Now okay
     with pytest.raises(TypeError, match="not defined"):
         bool(expr)
     with pytest.raises(TypeError):
@@ -2255,7 +2255,7 @@ def test_bool_eq_on_scalar_expressions(A):
 def test_bool_eq_on_scalar_expressions_no_auto(A):
     expr = A.reduce_scalar()
     with pytest.raises(TypeError, match="autocompute"):
-        expr == 47
+        assert expr == 47
     with pytest.raises(TypeError, match="autocompute"):
         bool(expr)
     with pytest.raises(TypeError, match="autocompute"):
@@ -2270,11 +2270,11 @@ def test_contains(A):
     assert (1, 0) not in A
 
     with pytest.raises(TypeError):
-        1 in A
+        assert 1 in A
     with pytest.raises(TypeError):
-        (1,) in A.T
+        assert (1,) in A.T
     with pytest.raises(TypeError, match="Invalid index"):
-        (1, [1, 2]) in A
+        assert (1, [1, 2]) in A
 
 
 def test_iter(A):

graphblas/tests/test_op.py

@@ -1082,9 +1082,9 @@ def _udt_identity(val):
     assert int in udt_identity
     assert operator.get_typed_op(udt_identity, udt) is udt_identity[udt]
     with pytest.raises(ValueError):
-        "badname" in binary.eq
+        assert "badname" in binary.eq
     with pytest.raises(ValueError):
-        "badname" in udt_identity
+        assert "badname" in udt_identity
 
     def _udt_getx(val):
         return val["x"]  # pragma: no cover