PYTHON-3120 Set up flake8 linting (mongodb#868)

Author: blink1073

.flake8

@@ -0,0 +1,30 @@
+[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
+    # B305 `.next()` is not a thing on Python 3
+    B305
+per-file-ignores =
+    # E402 module level import not at top of file
+    pymongo/__init__.py: E402
+
+    # G004 Logging statement uses f-string
+    pymongo/event_loggers.py: G004
+
+    # E402 module level import not at top of file
+    # B011 Do not call assert False since python -O removes these calls
+    # F405 'Foo' may be undefined, or defined from star imports
+    # E741 ambiguous variable name
+    # B007 Loop control variable 'foo' not used within the loop body
+    # F403 'from foo import *' used; unable to detect undefined names
+    # B001 Do not use bare `except:`
+    # E722 do not use bare 'except'
+    # E731 do not assign a lambda expression, use a def
+    # F811 redefinition of unused 'foo' from line XXX
+    # F841 local variable 'foo' is assigned to but never used
+    test/*: E402, B011, F405, E741, B007, F403, B001, E722, E731, F811, F841

.github/workflows/test-python.yml

@@ -31,6 +31,8 @@ jobs:
         uses: actions/setup-python@v2
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'pip'
+          cache-dependency-path: 'setup.py'
       - name: Start MongoDB
         uses: supercharge/[email protected]
         with:
@@ -53,6 +55,8 @@ jobs:
         uses: actions/setup-python@v2
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'pip'
+          cache-dependency-path: 'setup.py'
       - name: Install dependencies
         run: |
           python -m pip install -U pip mypy

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 
 repos:
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v3.4.0
+  rev: v4.1.0
   hooks:
   - id: check-added-large-files
   - id: check-case-conflict
@@ -24,17 +24,36 @@ repos:
     args: [--line-length=100]
 
 - repo: https://github.com/PyCQA/isort
-  rev: 5.7.0
+  rev: 5.10.1
   hooks:
   - id: isort
     files: \.py$
     args: [--profile=black]
 
+- repo: https://gitlab.com/pycqa/flake8
+  rev: 3.9.2
+  hooks:
+  - id: flake8
+    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
-  rev: v0.8.0.1
+  rev: v0.8.0.4
   hooks:
     - id: shellcheck
       name: shellcheck
       args: ["--severity=warning"]
+
+- repo: https://github.com/sirosen/check-jsonschema
+  rev: 0.11.0
+  hooks:
+    - id: check-jsonschema
+      name: "Check GitHub Workflows"
+      files: ^\.github/workflows/
+      types: [yaml]
+      args: ["--schemafile", "https://json.schemastore.org/github-workflow"]

bson/__init__.py

@@ -84,7 +84,7 @@
     cast,
 )
 
-from bson.binary import (
+from bson.binary import (  # noqa: F401
     ALL_UUID_SUBTYPES,
     CSHARP_LEGACY,
     JAVA_LEGACY,
@@ -513,7 +513,7 @@ def _bson_to_dict(data: Any, opts: Any) -> Any:
 
 
 if _USE_C:
-    _bson_to_dict = _cbson._bson_to_dict
+    _bson_to_dict = _cbson._bson_to_dict  # noqa: F811
 
 
 _PACK_FLOAT = struct.Struct("<d").pack
@@ -543,15 +543,15 @@ def _make_c_string_check(string: Union[str, bytes]) -> bytes:
     """Make a 'C' string, checking for embedded NUL characters."""
     if isinstance(string, bytes):
         if b"\x00" in string:
-            raise InvalidDocument("BSON keys / regex patterns must not " "contain a NUL character")
+            raise InvalidDocument("BSON keys / regex patterns must not contain a NUL character")
         try:
             _utf_8_decode(string, None, True)
             return string + b"\x00"
         except UnicodeError:
-            raise InvalidStringData("strings in documents must be valid " "UTF-8: %r" % string)
+            raise InvalidStringData("strings in documents must be valid UTF-8: %r" % string)
     else:
         if "\x00" in string:
-            raise InvalidDocument("BSON keys / regex patterns must not " "contain a NUL character")
+            raise InvalidDocument("BSON keys / regex patterns must not contain a NUL character")
         return cast(bytes, _utf_8_encode(string)[0]) + b"\x00"
 
 
@@ -562,7 +562,7 @@ def _make_c_string(string: Union[str, bytes]) -> bytes:
             _utf_8_decode(string, None, True)
             return string + b"\x00"
         except UnicodeError:
-            raise InvalidStringData("strings in documents must be valid " "UTF-8: %r" % string)
+            raise InvalidStringData("strings in documents must be valid UTF-8: %r" % string)
     else:
         return cast(bytes, _utf_8_encode(string)[0]) + b"\x00"
 
@@ -571,7 +571,7 @@ def _make_name(string: str) -> bytes:
     """Make a 'C' string suitable for a BSON key."""
     # Keys can only be text in python 3.
     if "\x00" in string:
-        raise InvalidDocument("BSON keys / regex patterns must not " "contain a NUL character")
+        raise InvalidDocument("BSON keys / regex patterns must not contain a NUL character")
     return cast(bytes, _utf_8_encode(string)[0]) + b"\x00"
 
 
@@ -846,7 +846,7 @@ def _name_value_to_bson(
 def _element_to_bson(key: Any, value: Any, check_keys: bool, opts: Any) -> bytes:
     """Encode a single key, value pair."""
     if not isinstance(key, str):
-        raise InvalidDocument("documents must have only string keys, " "key was %r" % (key,))
+        raise InvalidDocument("documents must have only string keys, key was %r" % (key,))
     if check_keys:
         if key.startswith("$"):
             raise InvalidDocument("key %r must not start with '$'" % (key,))
@@ -876,7 +876,7 @@ def _dict_to_bson(doc: Any, check_keys: bool, opts: Any, top_level: bool = True)
 
 
 if _USE_C:
-    _dict_to_bson = _cbson._dict_to_bson
+    _dict_to_bson = _cbson._dict_to_bson  # noqa: F811
 
 
 def _millis_to_datetime(millis: int, opts: Any) -> datetime.datetime:
@@ -1032,7 +1032,7 @@ def decode_all(
 
 
 if _USE_C:
-    decode_all = _cbson.decode_all
+    decode_all = _cbson.decode_all  # noqa: F811
 
 
 def _decode_selective(rawdoc: Any, fields: Any, codec_options: Any) -> Mapping[Any, Any]:

bson/binary.py

@@ -260,7 +260,7 @@ def from_uuid(
 
         if uuid_representation not in ALL_UUID_REPRESENTATIONS:
             raise ValueError(
-                "uuid_representation must be a value " "from bson.binary.UuidRepresentation"
+                "uuid_representation must be a value from bson.binary.UuidRepresentation"
             )
 
         if uuid_representation == UuidRepresentation.UNSPECIFIED:
@@ -310,7 +310,7 @@ def as_uuid(self, uuid_representation: int = UuidRepresentation.STANDARD) -> UUI
 
         if uuid_representation not in ALL_UUID_REPRESENTATIONS:
             raise ValueError(
-                "uuid_representation must be a value from " "bson.binary.UuidRepresentation"
+                "uuid_representation must be a value from bson.binary.UuidRepresentation"
             )
 
         if uuid_representation == UuidRepresentation.UNSPECIFIED:

bson/codec_options.py

@@ -23,12 +23,10 @@
     Any,
     Callable,
     Dict,
-    Generic,
     Iterable,
     MutableMapping,
     Optional,
     Type,
-    TypeVar,
     Union,
     cast,
 )
@@ -312,10 +310,10 @@ def __new__(
             raise TypeError("tz_aware must be True or False")
         if uuid_representation not in ALL_UUID_REPRESENTATIONS:
             raise ValueError(
-                "uuid_representation must be a value " "from bson.binary.UuidRepresentation"
+                "uuid_representation must be a value from bson.binary.UuidRepresentation"
             )
         if not isinstance(unicode_decode_error_handler, (str, None)):  # type: ignore
-            raise ValueError("unicode_decode_error_handler must be a string " "or None")
+            raise ValueError("unicode_decode_error_handler must be a string or None")
         if tzinfo is not None:
             if not isinstance(tzinfo, datetime.tzinfo):
                 raise TypeError("tzinfo must be an instance of datetime.tzinfo")

bson/dbref.py

@@ -35,7 +35,7 @@ def __init__(
         collection: str,
         id: Any,
         database: Optional[str] = None,
-        _extra: Mapping[str, Any] = {},
+        _extra: Optional[Mapping[str, Any]] = None,
         **kwargs: Any
     ) -> None:
         """Initialize a new :class:`DBRef`.
@@ -63,7 +63,7 @@ def __init__(
         self.__collection = collection
         self.__id = id
         self.__database = database
-        kwargs.update(_extra)
+        kwargs.update(_extra or {})
         self.__kwargs = kwargs
 
     @property

bson/json_util.py

@@ -283,7 +283,7 @@ def __new__(
         self.json_mode = json_mode
         if self.json_mode == JSONMode.RELAXED:
             if strict_number_long:
-                raise ValueError("Cannot specify strict_number_long=True with" " JSONMode.RELAXED")
+                raise ValueError("Cannot specify strict_number_long=True with JSONMode.RELAXED")
             if datetime_representation not in (None, DatetimeRepresentation.ISO8601):
                 raise ValueError(
                     "datetime_representation must be DatetimeRepresentation."
@@ -296,7 +296,7 @@ def __new__(
             self.strict_uuid = True
         elif self.json_mode == JSONMode.CANONICAL:
             if strict_number_long not in (None, True):
-                raise ValueError("Cannot specify strict_number_long=False with" " JSONMode.RELAXED")
+                raise ValueError("Cannot specify strict_number_long=False with JSONMode.RELAXED")
             if datetime_representation not in (None, DatetimeRepresentation.NUMBERLONG):
                 raise ValueError(
                     "datetime_representation must be DatetimeRepresentation."
@@ -581,11 +581,9 @@ def _parse_canonical_binary(doc: Any, json_options: JSONOptions) -> Union[Binary
     if not isinstance(b64, str):
         raise TypeError("$binary base64 must be a string: %s" % (doc,))
     if not isinstance(subtype, str) or len(subtype) > 2:
-        raise TypeError("$binary subType must be a string at most 2 " "characters: %s" % (doc,))
+        raise TypeError("$binary subType must be a string at most 2 characters: %s" % (doc,))
     if len(binary) != 2:
-        raise TypeError(
-            '$binary must include only "base64" and "subType" ' "components: %s" % (doc,)
-        )
+        raise TypeError('$binary must include only "base64" and "subType" components: %s' % (doc,))
 
     data = base64.b64decode(b64.encode())
     return _binary_or_uuid(data, int(subtype, 16), json_options)
@@ -686,7 +684,7 @@ def _parse_canonical_regex(doc: Any) -> Regex:
     opts = regex["options"]
     if not isinstance(opts, str):
         raise TypeError(
-            "Bad $regularExpression options, options must be " "string, was type %s" % (type(opts))
+            "Bad $regularExpression options, options must be string, was type %s" % (type(opts))
         )
     return Regex(regex["pattern"], opts)
 

bson/objectid.py

@@ -204,7 +204,7 @@ def __validate(self, oid: Any) -> None:
                 _raise_invalid_id(oid)
         else:
             raise TypeError(
-                "id must be an instance of (bytes, str, ObjectId), " "not %s" % (type(oid),)
+                "id must be an instance of (bytes, str, ObjectId), not %s" % (type(oid),)
             )
 
     @property

bson/raw_bson.py

@@ -51,8 +51,7 @@
 overhead of decoding or encoding BSON.
 """
 
-from collections.abc import Mapping as _Mapping
-from typing import Any, ItemsView, Iterator, Mapping, Optional, cast
+from typing import Any, ItemsView, Iterator, Mapping, Optional
 
 from bson import _get_object_size, _raw_to_dict
 from bson.codec_options import _RAW_BSON_DOCUMENT_MARKER

bson/tz_util.py

@@ -15,7 +15,7 @@
 """Timezone related utilities for BSON."""
 
 from datetime import datetime, timedelta, tzinfo
-from typing import Any, Optional, Tuple, Union
+from typing import Optional, Tuple, Union
 
 ZERO: timedelta = timedelta(0)
 

doc/conf.py

@@ -9,7 +9,7 @@
 
 sys.path[0:0] = [os.path.abspath("..")]
 
-import pymongo
+import pymongo  # noqa
 
 # -- General configuration -----------------------------------------------------
 

green_framework_test.py

@@ -59,7 +59,7 @@ def run(framework_name, *args):
 
     # Run the tests.
     sys.argv[:] = ["setup.py", "test"] + list(args)
-    import setup
+    import setup  # noqa
 
 
 def main():
@@ -87,7 +87,7 @@ def main():
             list_frameworks()
             sys.exit()
         else:
-            assert False, "unhandled option"
+            raise AssertionError("unhandled option")
 
     if not args:
         print(usage)

gridfs/__init__.py

@@ -35,11 +35,10 @@
 )
 from pymongo import ASCENDING, DESCENDING
 from pymongo.client_session import ClientSession
-from pymongo.collation import Collation
 from pymongo.collection import Collection
-from pymongo.common import UNAUTHORIZED_CODES, validate_string
+from pymongo.common import validate_string
 from pymongo.database import Database
-from pymongo.errors import ConfigurationError, OperationFailure
+from pymongo.errors import ConfigurationError
 from pymongo.read_preferences import _ServerMode
 from pymongo.write_concern import WriteConcern
 
@@ -83,7 +82,7 @@ def __init__(self, database: Database, collection: str = "fs"):
         database = _clear_entity_type_registry(database)
 
         if not database.write_concern.acknowledged:
-            raise ConfigurationError("database must use " "acknowledged write_concern")
+            raise ConfigurationError("database must use acknowledged write_concern")
 
         self.__collection = database[collection]
         self.__files = self.__collection.files