ARROW-59 Set up flake8 config (#54)

Author: blink1073

.github/workflows/release-python.yml

@@ -22,6 +22,8 @@ jobs:
         uses: actions/setup-python@v2
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'pip'
+          cache-dependency-path: '**/setup.cfg'
       - name: Build wheels
         working-directory: ./bindings/python
         shell: bash

.github/workflows/test-python.yml

@@ -41,6 +41,8 @@ jobs:
         uses: actions/setup-python@v2
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'pip'
+          cache-dependency-path: '**/setup.cfg'
       - name: Start MongoDB on Linux
         if: ${{ startsWith(runner.os, 'Linux') }}
         uses: supercharge/[email protected]

.pre-commit-config.yaml

@@ -30,6 +30,20 @@ repos:
     files: \.py$
     args: [--profile=black]
 
+- repo: https://gitlab.com/pycqa/flake8
+  rev: 4.0.1
+  hooks:
+  - id: flake8
+    args: [--config=bindings/python/.flake8]
+    types: [file]
+    files: \.(py|pyx|pxd)$
+    additional_dependencies: [
+        'flake8-bugbear==20.1.4',
+        'flake8-logging-format==0.6.0',
+        'flake8-implicit-str-concat==0.2.0',
+    ]
+
+
 # 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

bindings/python/.flake8

@@ -0,0 +1,15 @@
+[flake8]
+max-line-length = 100
+enable-extensions = G
+extend-ignore =
+    G200, G202,
+    # black adds spaces around ':'
+    E203,
+    # E501 line too long (let black handle line length)
+    E501
+per-file-ignores =
+    # E227 missing whitespace around bitwise or shift operator
+    # E225 missing whitespace around operator
+    # E999 SyntaxError: invalid syntax
+    bindings/python/pymongoarrow/*.pyx: E227,E225,E999
+    bindings/python/pymongoarrow/*.pxd: E227,E225,E999

bindings/python/MANIFEST.in

@@ -7,6 +7,7 @@ exclude THIRD-PARTY-NOTICES
 exclude release.sh
 exclude addtags.py
 exclude benchmark.py
+exclude .flake8
 
 graft pymongoarrow
 

bindings/python/benchmark.py

@@ -10,8 +10,7 @@
 import pandas as pd
 import pyarrow
 import pymongo
-from bson import BSON, CodecOptions, Int64, ObjectId
-from bson.raw_bson import RawBSONDocument
+from bson import BSON, Int64, ObjectId
 from pymongoarrow.api import Schema, find_arrow_all, find_numpy_all, find_pandas_all
 
 assert pymongo.has_c()
@@ -125,9 +124,9 @@ def to_numpy(use_large):
 @bench("conventional-to-pandas")
 def conventional_pandas(use_large):
     collection = db[collection_names[use_large]]
-    dtype = dtypes[use_large]
+    _ = dtypes[use_large]
     cursor = collection.find(projection={"_id": 0})
-    data_frame = pd.DataFrame(list(cursor))
+    _ = pd.DataFrame(list(cursor))
 
 
 @bench("pymongoarrow-to-pandas")

bindings/python/docs/source/conf.py

@@ -10,7 +10,6 @@
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 #
-import os
 import os.path as p
 
 # -- Project information -----------------------------------------------------

bindings/python/pymongoarrow/__init__.py

@@ -15,8 +15,8 @@
 import warnings
 
 # We must import pyarrow before attempting to load the Cython module.
-import pyarrow
-from pymongoarrow.version import _MIN_LIBBSON_VERSION, __version__
+import pyarrow  # noqa: F401
+from pymongoarrow.version import _MIN_LIBBSON_VERSION, __version__  # noqa: F401
 
 try:
     from pkg_resources import parse_version as _parse_version

bindings/python/pymongoarrow/api.py

@@ -59,7 +59,7 @@ def find_arrow_all(collection, query, *, schema, **kwargs):
     for opt in ("cursor_type",):
         if kwargs.pop(opt, None):
             warnings.warn(
-                f"Ignoring option {opt!r} as it is not supported by " "PyMongoArrow",
+                f"Ignoring option {opt!r} as it is not supported by PyMongoArrow",
                 UserWarning,
                 stacklevel=2,
             )
@@ -99,7 +99,7 @@ def aggregate_arrow_all(collection, pipeline, *, schema, **kwargs):
     for opt in ("batchSize", "useCursor"):
         if kwargs.pop(opt, None):
             warnings.warn(
-                f"Ignoring option {opt!r} as it is not supported by " "PyMongoArrow",
+                f"Ignoring option {opt!r} as it is not supported by PyMongoArrow",
                 UserWarning,
                 stacklevel=2,
             )

bindings/python/pymongoarrow/errors.py

@@ -14,7 +14,7 @@
 
 """Exceptions raised by PyMongoArrow."""
 
-from bson.errors import InvalidBSON
+from bson.errors import InvalidBSON  # noqa: F401
 
 
 class PyMongoArrowError(Exception):