style: update lints

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 
 repos:
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.5.0
+  rev: v6.0.0
   hooks:
   - id: check-added-large-files
   - id: check-case-conflict
@@ -19,14 +19,14 @@ repos:
 
 - repo: https://github.com/astral-sh/ruff-pre-commit
   # Ruff version.
-  rev: v0.1.3
+  rev: v0.15.6
   hooks:
     - id: ruff
       args: ["--fix", "--show-fixes"]
     - id: ruff-format
 
 - repo: https://github.com/adamchainz/blacken-docs
-  rev: "1.16.0"
+  rev: "1.20.0"
   hooks:
   - id: blacken-docs
     additional_dependencies:
@@ -40,43 +40,43 @@ repos:
     - id: rst-inline-touching-normal
 
 - repo: https://github.com/rstcheck/rstcheck
-  rev: v6.2.0
+  rev: v6.2.5
   hooks:
   - id: rstcheck
     additional_dependencies: [sphinx]
     args: ["--ignore-directives=doctest,testsetup,todo,automodule","--ignore-substitutions=release", "--report-level=error"]
 
 - repo: https://github.com/PyCQA/flake8
-  rev: 3.9.2
+  rev: 7.3.0
   hooks:
   - id: flake8
     files: \.rst$
     additional_dependencies: [
         'flake8-rst==0.8.0',
-        'flake8-bugbear==20.1.4',
-        'flake8-logging-format==0.6.0',
-        'flake8-implicit-str-concat==0.2.0',
+        'flake8-bugbear==25.11.29',
+        'flake8-logging-format==0.9.0',
+        'flake8-implicit-str-concat==0.6.0',
     ]
 
 # We use the Python version instead of the original version which seems to require Docker
 # https://github.com/koalaman/shellcheck-precommit
 - repo: https://github.com/shellcheck-py/shellcheck-py
-  rev: v0.9.0.6
+  rev: v0.11.0.1
   hooks:
     - id: shellcheck
       name: shellcheck
       args: ["--severity=warning"]
       stages: [manual]
 
 - repo: https://github.com/PyCQA/doc8
-  rev: v1.1.1
+  rev: v2.0.0
   hooks:
     - id: doc8
       args: ["--ignore=D001"]  # ignore line length
       stages: [manual]
 
 - repo: https://github.com/sirosen/check-jsonschema
-  rev: 0.27.0
+  rev: 0.37.0
   hooks:
     - id: check-jsonschema
       name: "Check GitHub Workflows"
@@ -86,7 +86,7 @@ repos:
       stages: [manual]
 
 - repo: https://github.com/ariebovenberg/slotscheck
-  rev: v0.17.0
+  rev: v0.19.1
   hooks:
   - id: slotscheck
     files: \.py$
@@ -95,13 +95,13 @@ repos:
     args: ["--no-strict-imports"]
 
 - repo: https://github.com/MarcoGorelli/cython-lint
-  rev: v0.16.2
+  rev: v0.19.0
   hooks:
   - id: cython-lint
     args: ["--no-pycodestyle"]
 
 - repo: https://github.com/codespell-project/codespell
-  rev: "v2.2.6"
+  rev: "v2.4.2"
   hooks:
   - id: codespell
     # Examples of errors or updates to justify the exceptions:

bindings/python/benchmarks/benchmarks.py

@@ -201,8 +201,7 @@ def setup(self):
         )
         coll.insert_many([base_dict.copy() for _ in range(N_DOCS)])
         print(
-            "%d docs, %dk each with %d keys"
-            % (N_DOCS, len(BSON.encode(base_dict)) // 1024, len(base_dict))
+            f"{N_DOCS} docs, {len(BSON.encode(base_dict)) // 1024} each with {len(base_dict)} keys"
         )
 
     # All of the following tests are being skipped because NumPy/Pandas/Polars do not work with nested arrays.
@@ -248,8 +247,7 @@ def setup(self):
         )
         coll.insert_many([base_dict.copy() for _ in range(N_DOCS)])
         print(
-            "%d docs, %dk each with %d keys"
-            % (N_DOCS, len(BSON.encode(base_dict)) // 1024, len(base_dict))
+            f"{N_DOCS} docs, {len(BSON.encode(base_dict)) // 1024} each with {len(base_dict)} keys"
         )
 
     # All of the following tests are being skipped because NumPy/Pandas/Polars do not work with nested documents.
@@ -287,8 +285,7 @@ def setup(self):
         )
         coll.insert_many([base_dict.copy() for _ in range(N_DOCS)])
         print(
-            "%d docs, %dk each with %d keys"
-            % (N_DOCS, len(BSON.encode(base_dict)) // 1024, len(base_dict))
+            f"{N_DOCS} docs, {len(BSON.encode(base_dict)) // 1024} each with {len(base_dict)} keys"
         )
 
 
@@ -304,8 +301,7 @@ def setup(self):
         base_dict = dict([(k, math.pi) for k in self.large_doc_keys])
         coll.insert_many([base_dict.copy() for _ in range(N_DOCS)])
         print(
-            "%d docs, %dk each with %d keys"
-            % (N_DOCS, len(BSON.encode(base_dict)) // 1024, len(base_dict))
+            f"{N_DOCS} docs, {len(BSON.encode(base_dict)) // 1024} each with {len(base_dict)} keys"
         )
 
 
@@ -324,8 +320,7 @@ def setup(self):
         )
         coll.insert_many([base_dict.copy() for _ in range(N_DOCS)])
         print(
-            "%d docs, %dk each with %d keys"
-            % (N_DOCS, len(BSON.encode(base_dict)) // 1024, len(base_dict))
+            f"{N_DOCS} docs, {len(BSON.encode(base_dict)) // 1024} each with {len(base_dict)} keys"
         )
 
     # This must be skipped because arrow can't read the Decimal128Type
@@ -348,8 +343,7 @@ def setup(self):
         base_dict = dict([(k, Decimal128(k)) for k in self.large_doc_keys])
         coll.insert_many([base_dict.copy() for _ in range(N_DOCS)])
         print(
-            "%d docs, %dk each with %d keys"
-            % (N_DOCS, len(BSON.encode(base_dict)) // 1024, len(base_dict))
+            f"{N_DOCS} docs, {len(BSON.encode(base_dict)) // 1024} each with {len(base_dict)} keys"
         )
 
     # This must be skipped because arrow can't read the Decimal128Type
@@ -371,8 +365,7 @@ def setup(self):
         base_dict = dict([("x", 1), ("y", math.pi)])
         coll.insert_many([base_dict.copy() for _ in range(N_DOCS)])
         print(
-            "%d docs, %dk each with %d keys"
-            % (N_DOCS, len(BSON.encode(base_dict)) // 1024, len(base_dict))
+            f"{N_DOCS} docs, {len(BSON.encode(base_dict)) // 1024} each with {len(base_dict)} keys"
         )
         self.arrow_table = find_arrow_all(db.benchmark, {}, schema=self.schema)
         self.pandas_table = find_pandas_all(db.benchmark, {}, schema=self.schema)
@@ -391,8 +384,7 @@ def setup(self):
         base_dict = dict([(k, math.pi) for k in self.large_doc_keys])
         coll.insert_many([base_dict.copy() for _ in range(N_DOCS)])
         print(
-            "%d docs, %dk each with %d keys"
-            % (N_DOCS, len(BSON.encode(base_dict)) // 1024, len(base_dict))
+            f"{N_DOCS} docs, {len(BSON.encode(base_dict)) // 1024} each with {len(base_dict)} keys"
         )
         self.arrow_table = find_arrow_all(db.benchmark, {}, schema=self.schema)
         self.pandas_table = find_pandas_all(db.benchmark, {}, schema=self.schema)

bindings/python/pymongoarrow/__init__.py

@@ -42,8 +42,5 @@
 
 if libbson_version is not None and _parse_version is not None:  # noqa: SIM102
     if _parse_version(libbson_version) < _parse_version(_MIN_LIBBSON_VERSION):
-        msg = (
-            f"Expected libbson version {_MIN_LIBBSON_VERSION} or greater, "
-            f"found {libbson_version}"
-        )
+        msg = f"Expected libbson version {_MIN_LIBBSON_VERSION} or greater, found {libbson_version}"
         raise ImportError(msg)

bindings/python/pymongoarrow/api.py

@@ -64,16 +64,16 @@
 from pymongoarrow.types import _validate_schema, get_numpy_type
 
 __all__ = [
+    "Schema",
     "aggregate_arrow_all",
-    "find_arrow_all",
-    "aggregate_pandas_all",
-    "find_pandas_all",
     "aggregate_numpy_all",
-    "find_numpy_all",
+    "aggregate_pandas_all",
     "aggregate_polars_all",
+    "find_arrow_all",
+    "find_numpy_all",
+    "find_pandas_all",
     "find_polars_all",
     "write",
-    "Schema",
 ]
 
 

bindings/python/pymongoarrow/lib.pyx

@@ -836,7 +836,7 @@ cdef class DocumentBuilder(_ArrayBuilderBase):
 
     def finish(self):
         # Fields must be in order if we were given a schema.
-        return list(f.decode('utf-8') for f in self.field_map)
+        return [f.decode('utf-8') for f in self.field_map]
 
 
 cdef class ListBuilder(_ArrayBuilderBase):

bindings/python/pymongoarrow/pandas_types.py

@@ -183,6 +183,9 @@ def isna(self):
             dtype=bool,
         )
 
+    def __hash__(self):
+        return hash(self.data)
+
     def __eq__(self, other):
         return self.data == other
 
@@ -267,6 +270,9 @@ def __arrow_array__(self, type=None):
 
         return pa.array(self.data, type=BinaryType(self.dtype.subtype))
 
+    def __hash__(self):
+        return super().__hash__()
+
     def __eq__(self, other):
         # Binary types do not support element-wise comparison.
         if isinstance(other, Binary):
@@ -349,6 +355,9 @@ def __init__(self, values, dtype, copy=False) -> None:
     def _default_dtype(self):
         return PandasCode()
 
+    def __hash__(self):
+        return super().__hash__()
+
     def __eq__(self, other):
         # Code types do not support element-wise comparison.
         if isinstance(other, Code):

bindings/python/pymongoarrow/polars_types.py

@@ -22,6 +22,9 @@
 if pl:
 
     class PolarsExtensionBase(pl.datatypes.BaseExtension):
+        def __hash__(self):
+            return hash(self.ext_name(), self.ext_storage())
+
         def __eq__(self, other):
             return (
                 isinstance(other, self.__class__)

bindings/python/pymongoarrow/schema.py

@@ -84,6 +84,9 @@ def _get_field_projection_value(self, fname, ftype, projection):
         projection[fname] = value
         return projection
 
+    def __hash__(self):
+        return hash(self.typemap)
+
     def __eq__(self, other):
         if isinstance(other, type(self)):
             return self.typemap == other.typemap

bindings/python/pymongoarrow/types.py

@@ -255,7 +255,7 @@ def _is_code(obj):
     Decimal128: lambda _: Decimal128Type(),
     str: lambda _: string(),
     bool: lambda _: bool_(),
-    Binary: lambda subtype: BinaryType(subtype),
+    Binary: BinaryType,
     Code: lambda _: CodeType(),
 }
 

bindings/python/pyproject.toml

@@ -145,6 +145,7 @@ select = [
 ignore = [
   "PLR",        # Design related pylint codes
   "RUF012",     # Mutable class attributes should be annotated with `typing.ClassVar`
+  "PLC0415",    # `import` should be at the top-level of a file
 ]
 unfixable = [
 ]

bindings/python/test/conftest.py

@@ -11,10 +11,10 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from test import client_context
-
 import pytest
 
+from test import client_context
+
 try:
     import pandas as pd
 

bindings/python/test/pandas_types/test_binary.py

@@ -11,13 +11,12 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from test.pandas_types.util import base_make_data
-
 import numpy as np
 import pytest
 from bson import Binary
 
 from pymongoarrow.pandas_types import PandasBinary, PandasBinaryArray
+from test.pandas_types.util import base_make_data
 
 try:
     from pandas.tests.extension import base

bindings/python/test/pandas_types/test_code.py

@@ -11,13 +11,12 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from test.pandas_types.util import base_make_data
-
 import numpy as np
 import pytest
 from bson import Code
 
 from pymongoarrow.pandas_types import PandasCode, PandasCodeArray
+from test.pandas_types.util import base_make_data
 
 try:
     from pandas.tests.extension import base

bindings/python/test/pandas_types/test_decimal128.py

@@ -11,13 +11,12 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from test.pandas_types.util import base_make_data
-
 import numpy as np
 import pytest
 from bson import Decimal128
 
 from pymongoarrow.pandas_types import PandasDecimal128, PandasDecimal128Array
+from test.pandas_types.util import base_make_data
 
 try:
     from pandas.tests.extension import base

bindings/python/test/pandas_types/test_objectid.py

@@ -11,13 +11,12 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from test.pandas_types.util import base_make_data
-
 import numpy as np
 import pytest
 from bson import ObjectId
 
 from pymongoarrow.pandas_types import PandasObjectId, PandasObjectIdArray
+from test.pandas_types.util import base_make_data
 
 try:
     from pandas.tests.extension import base