diff --git a/CHANGELOG.md b/CHANGELOG.md
index 72973411..256f6f25 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -11,6 +11,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Changes
+- make ruff linter config opt-out, instead of opt-in
+
### Deprecated
### Removed
diff --git a/mex/common/backend_api/connector.py b/mex/common/backend_api/connector.py
index 94731488..2ee350c1 100644
--- a/mex/common/backend_api/connector.py
+++ b/mex/common/backend_api/connector.py
@@ -145,7 +145,7 @@ def get_merged_item(
Returns:
A single merged item
"""
- # XXX stop-gap until the backend has a proper get merged item endpoint (MX-1669)
+ # TODO(ND): stop-gap until backend has proper get merged item endpoint (MX-1669)
response = self.request(
method="GET",
endpoint="merged-item",
@@ -158,7 +158,8 @@ def get_merged_item(
try:
return response_model.items[0]
except IndexError:
- raise HTTPError("merged item was not found") from None
+ msg = "merged item was not found"
+ raise HTTPError(msg) from None
def preview_merged_item(
self,
diff --git a/mex/common/cli.py b/mex/common/cli.py
index d9424f18..d17a529e 100644
--- a/mex/common/cli.py
+++ b/mex/common/cli.py
@@ -137,13 +137,13 @@ def _callback(
func()
except (Abort, BdbQuit, Exit, KeyboardInterrupt): # pragma: no cover
context.exit(130)
- except Exception as error:
+ except Exception:
# an error occurred, let's print the traceback
logger.error(click.style(format_exc(), fg="red"))
if settings.debug: # pragma: no cover
# if we are in debug mode, jump into interactive debugging.
pdb.post_mortem(sys.exc_info()[2])
- raise error
+ raise
# if not in debug mode, exit with code 1.
logger.error("exit")
context.exit(1)
diff --git a/mex/common/connector/http.py b/mex/common/connector/http.py
index e6e1ef12..716de1de 100644
--- a/mex/common/connector/http.py
+++ b/mex/common/connector/http.py
@@ -5,7 +5,7 @@
import backoff
import requests
-from requests import HTTPError, RequestException, Response
+from requests import HTTPError, RequestException, Response, codes
from mex.common.connector import BaseConnector
from mex.common.settings import BaseSettings
@@ -30,7 +30,7 @@ def _set_session(self) -> None:
"""Create and set request session."""
settings = BaseSettings.get()
self.session = requests.Session()
- self.session.verify = settings.verify_session # type: ignore
+ self.session.verify = settings.verify_session # type: ignore[assignment]
def _set_authentication(self) -> None:
"""Authenticate to the host."""
@@ -94,23 +94,25 @@ def request(
response=response,
) from error
- if response.status_code == 204:
+ if response.status_code == codes.no_content:
return {}
return cast(dict[str, Any], response.json())
@backoff.on_predicate(
backoff.fibo,
- lambda response: cast(Response, response).status_code >= 500,
+ lambda response: cast(Response, response).status_code
+ >= codes.internal_server_error,
max_tries=4,
)
@backoff.on_predicate(
backoff.fibo,
- lambda response: cast(Response, response).status_code == 429,
+ lambda response: cast(Response, response).status_code
+ == codes.too_many_requests,
max_tries=10,
)
@backoff.on_predicate(
backoff.fibo,
- lambda response: cast(Response, response).status_code == 403,
+ lambda response: cast(Response, response).status_code == codes.forbidden,
max_tries=10,
)
@backoff.on_exception(backoff.fibo, RequestException, max_tries=6)
diff --git a/mex/common/context.py b/mex/common/context.py
index ba6707cf..96857f38 100644
--- a/mex/common/context.py
+++ b/mex/common/context.py
@@ -51,11 +51,12 @@ def load(self, cls: type[_SingletonT]) -> _SingletonT:
self._singleton = cls()
return self._singleton
if not issubclass(type(self._singleton), cls):
- raise RuntimeError(
+ msg = (
f"requested class ({cls}) is not a parent class of loaded class "
f"({type(self._singleton)}). "
f"Did you initialize {cls} upon startup?"
)
+ raise RuntimeError(msg) # noqa: TRY004
return self._singleton
def push(self, instance: _SingletonT) -> None:
diff --git a/mex/common/extract.py b/mex/common/extract.py
index 688806ad..cb9755c2 100644
--- a/mex/common/extract.py
+++ b/mex/common/extract.py
@@ -59,10 +59,12 @@ def parse_csv(
) as reader:
for chunk in reader:
for index, row in chunk.iterrows():
- row.replace(to_replace=np.nan, value=None, inplace=True)
- row.replace(regex=r"^\s*$", value=None, inplace=True)
try:
- model = into.model_validate(row.to_dict())
+ model = into.model_validate(
+ row.replace(to_replace=np.nan, value=None)
+ .replace(regex=r"^\s*$", value=None)
+ .to_dict()
+ )
logger.info(
"parse_csv - %s %s - OK",
into.__name__,
diff --git a/mex/common/identity/registry.py b/mex/common/identity/registry.py
index b133ea6e..0525aa9f 100644
--- a/mex/common/identity/registry.py
+++ b/mex/common/identity/registry.py
@@ -21,7 +21,8 @@ def register_provider(key: Hashable, provider_cls: type[BaseProvider]) -> None:
RuntimeError: When the `key` is already registered
"""
if key in _PROVIDER_REGISTRY:
- raise RuntimeError(f"Already registered identity provider: {key}")
+ msg = f"Already registered identity provider: {key}"
+ raise RuntimeError(msg)
_PROVIDER_REGISTRY[key] = provider_cls
@@ -41,9 +42,8 @@ def get_provider() -> BaseProvider:
if settings.identity_provider in _PROVIDER_REGISTRY:
provider_cls = _PROVIDER_REGISTRY[settings.identity_provider]
return provider_cls.get()
- raise RuntimeError(
- f"Identity provider not implemented: {settings.identity_provider}"
- )
+ msg = f"Identity provider not implemented: {settings.identity_provider}"
+ raise RuntimeError(msg)
# register the default providers shipped with mex-common
diff --git a/mex/common/ldap/connector.py b/mex/common/ldap/connector.py
index debaf93b..6f93e716 100644
--- a/mex/common/ldap/connector.py
+++ b/mex/common/ldap/connector.py
@@ -43,7 +43,8 @@ def __init__(self) -> None:
)
self._connection = connection.__enter__()
if not self._is_service_available():
- raise MExError(f"LDAP service not available at url: {host}:{port}")
+ msg = f"LDAP service not available at url: {host}:{port}"
+ raise MExError(msg)
def _is_service_available(self) -> bool:
try:
@@ -197,15 +198,17 @@ def get_functional_account(
)
)
if not functional_accounts:
- raise EmptySearchResultError(
+ msg = (
"Cannot find AD functional account for filters "
f"'objectGUID: {objectGUID}, {filters}'"
)
+ raise EmptySearchResultError(msg)
if len(functional_accounts) > 1:
- raise FoundMoreThanOneError(
+ msg = (
"Found multiple AD functional accounts for filters "
f"'objectGUID: {objectGUID}, {filters}'"
)
+ raise FoundMoreThanOneError(msg)
return functional_accounts[0]
def get_person(
@@ -235,15 +238,17 @@ def get_person(
)
)
if not persons:
- raise EmptySearchResultError(
+ msg = (
f"Cannot find AD person for filters 'objectGUID: {objectGUID}, "
f"employeeID: {employeeID}, {filters}'"
)
+ raise EmptySearchResultError(msg)
if len(persons) > 1:
- raise FoundMoreThanOneError(
+ msg = (
f"Found multiple AD persons for filters 'objectGUID: {objectGUID}, "
f"employeeID: {employeeID}, {filters}'"
)
+ raise FoundMoreThanOneError(msg)
return persons[0]
def get_unit(self, **filters: str) -> LDAPUnit:
@@ -260,9 +265,9 @@ def get_unit(self, **filters: str) -> LDAPUnit:
"""
units = list(self.get_units(**filters))
if not units:
- raise EmptySearchResultError(f"Cannot find AD unit for filters '{filters}'")
+ msg = f"Cannot find AD unit for filters '{filters}'"
+ raise EmptySearchResultError(msg)
if len(units) > 1:
- raise FoundMoreThanOneError(
- f"Found multiple AD units for filters '{filters}'"
- )
+ msg = f"Found multiple AD units for filters '{filters}'"
+ raise FoundMoreThanOneError(msg)
return units[0]
diff --git a/mex/common/ldap/extract.py b/mex/common/ldap/extract.py
index 89854dd0..7fa371e2 100644
--- a/mex/common/ldap/extract.py
+++ b/mex/common/ldap/extract.py
@@ -28,7 +28,8 @@ def _get_merged_ids_by_attribute(
MergedPersonIdentifiers
"""
if attribute not in LDAPPerson.model_fields:
- raise RuntimeError(f"Not a valid LDAPPerson field: {attribute}")
+ msg = f"Not a valid LDAPPerson field: {attribute}"
+ raise RuntimeError(msg)
merged_ids_by_attribute = defaultdict(list)
provider = get_provider()
for person in persons:
diff --git a/mex/common/ldap/transform.py b/mex/common/ldap/transform.py
index 106c361d..29364450 100644
--- a/mex/common/ldap/transform.py
+++ b/mex/common/ldap/transform.py
@@ -100,15 +100,16 @@ def transform_ldap_person_to_mex_person(
if d and (unit := units_by_identifier_in_primary_source.get(d.lower()))
]
if not member_of:
- raise MExError(
+ msg = (
"No unit or department found for LDAP department "
f"'{ldap_person.department}' or departmentNumber "
f"'{ldap_person.departmentNumber}'"
)
+ raise MExError(msg)
return ExtractedPerson(
identifierInPrimarySource=str(ldap_person.objectGUID),
hadPrimarySource=primary_source.stableTargetId,
- affiliation=[], # TODO resolve organization for person.company/RKI
+ affiliation=[], # TODO(HS): resolve organization for person.company/RKI
email=ldap_person.mail,
familyName=[ldap_person.sn],
fullName=[ldap_person.displayName] if ldap_person.displayName else [],
@@ -184,11 +185,11 @@ def analyse_person_string(string: str) -> list[PersonName]:
return [name for strings in split for name in analyse_person_string(strings)]
# split on comma if there is more than one
- if len(split := re.split(r",", string)) > 2:
+ if len(split := re.split(r",", string)) > 2: # noqa: PLR2004
return [name for strings in split for name in analyse_person_string(strings)]
# split on single commas only if there are more than three words
- if len(split := re.split(r",", string)) == 2 and string.strip().count(" ") > 2:
+ if len(split := re.split(r",", string)) == 2 and string.strip().count(" ") > 2: # noqa: PLR2004
return [name for strings in split for name in analyse_person_string(strings)]
# split into surname and given name
@@ -209,7 +210,7 @@ def analyse_person_string(string: str) -> list[PersonName]:
return [PersonName(surname=split[0], full_name=full_name)]
# return surname and given name
- if len(split) == 2:
+ if len(split) == 2: # noqa: PLR2004
return [PersonName(surname=split[1], given_name=split[0], full_name=full_name)]
# found no one
diff --git a/mex/common/models/base/model.py b/mex/common/models/base/model.py
index e5ac4802..7092d140 100644
--- a/mex/common/models/base/model.py
+++ b/mex/common/models/base/model.py
@@ -143,7 +143,8 @@ def _convert_list_to_non_list(cls, field_name: str, value: list[Any]) -> Any:
# if we have just one entry, we can safely unpack it
return value[0]
# we cannot unambiguously unpack more than one value
- raise ValueError(f"got multiple values for {field_name}")
+ msg = f"got multiple values for {field_name}"
+ raise ValueError(msg)
@classmethod
def _fix_value_listyness_for_field(cls, field_name: str, value: Any) -> Any:
@@ -186,10 +187,11 @@ def verify_computed_field_consistency(
if not isinstance(data, MutableMapping):
# data is not a dictionary: we can't "pop" values from that,
# so we can't safely do a before/after comparison
- raise AssertionError(
+ msg = (
"Input should be a valid dictionary, validating other types is not "
"supported for models with computed fields."
)
+ raise AssertionError(msg) # noqa: TRY004
custom_values = {
field: value
for field in cls.model_computed_fields
@@ -198,7 +200,8 @@ def verify_computed_field_consistency(
result = handler(data)
computed_values = result.model_dump(include=set(custom_values))
if computed_values != custom_values:
- raise ValueError("Cannot set computed fields to custom values!")
+ msg = "Cannot set computed fields to custom values!"
+ raise ValueError(msg)
return result
@model_validator(mode="wrap")
@@ -223,9 +226,9 @@ def fix_listyness(cls, data: Any, handler: ValidatorFunctionWrapHandler) -> Any:
Returns:
data with fixed list shapes
"""
- # XXX This needs to be a "wrap" validator that is defined *after* the computed
- # field model validator, so it runs *before* the computed field validator.
- # Sigh, see https://github.com/pydantic/pydantic/discussions/7434
+ # TODO(ND): This needs to be a "wrap" validator that is defined *after* the
+ # computed field model validator, so it runs *before* the computed field
+ # validator. Sigh, see https://github.com/pydantic/pydantic/discussions/7434
if isinstance(data, MutableMapping):
for name, value in data.items():
field_name = cls._get_alias_lookup().get(name, name)
diff --git a/mex/common/models/consent.py b/mex/common/models/consent.py
index 3e62ee0b..f7c6e233 100644
--- a/mex/common/models/consent.py
+++ b/mex/common/models/consent.py
@@ -1,3 +1,2 @@
-# XXX this is a forward-compatibility hint for feature/model-update-v3:
-# when this gets merged with model v3, remove the
-# `Annotated[..., Field(examples=["https://mex..."])]` from all enum fields
+# TODO(ND): when this gets merged with feature/model-update-v3, remove the
+# `Annotated[..., Field(examples=["https://mex..."])]` from all enum fields
diff --git a/mex/common/organigram/transform.py b/mex/common/organigram/transform.py
index e3957740..829bb347 100644
--- a/mex/common/organigram/transform.py
+++ b/mex/common/organigram/transform.py
@@ -42,7 +42,7 @@ def transform_organigram_units_to_organizational_units(
for extracted_unit in extracted_unit_by_id_in_primary_source.values():
identifier_in_primary_source = extracted_unit.identifierInPrimarySource
- if (
+ if ( # noqa: SIM102
parent_identifier_in_primary_source
:= parent_id_in_primary_source_by_id_in_primary_source.get(
identifier_in_primary_source
diff --git a/mex/common/settings.py b/mex/common/settings.py
index fbdd7db4..e5fd3b6d 100644
--- a/mex/common/settings.py
+++ b/mex/common/settings.py
@@ -208,7 +208,7 @@ def get_env_name(cls, name: str) -> str:
case_sensitive=cls.model_config.get("case_sensitive", False),
env_prefix=cls.model_config.get("env_prefix", ""),
)
- env_info = env_settings._extract_field_info(field, name)
+ env_info = env_settings._extract_field_info(field, name) # noqa: SLF001
return env_info[0][1].upper()
@model_validator(mode="after")
diff --git a/mex/common/sinks/ndjson.py b/mex/common/sinks/ndjson.py
index 565101e7..619b5b63 100644
--- a/mex/common/sinks/ndjson.py
+++ b/mex/common/sinks/ndjson.py
@@ -35,7 +35,7 @@ def write_ndjson(
handle = file_handles[class_name]
except KeyError:
file_name = Path(settings.work_dir, f"{class_name}.ndjson")
- writer = open(file_name, "a+", encoding="utf-8")
+ writer = open(file_name, "a+", encoding="utf-8") # noqa: SIM115
file_handles[class_name] = handle = stack.enter_context(writer)
logger.info(
"write_ndjson - writing %s to file %s",
diff --git a/mex/common/transform.py b/mex/common/transform.py
index 521421a6..e394894e 100644
--- a/mex/common/transform.py
+++ b/mex/common/transform.py
@@ -16,7 +16,7 @@
class MExEncoder(json.JSONEncoder):
"""Custom JSON encoder that can handle pydantic models, enums and UUIDs."""
- def default(self, obj: Any) -> Any:
+ def default(self, obj: Any) -> Any: # noqa: PLR0911
"""Implement custom serialization rules."""
if isinstance(obj, PydanticModel):
return obj.model_dump()
@@ -106,7 +106,9 @@ def to_key_and_values(dct: dict[str, Any]) -> Iterable[tuple[str, list[Any]]]:
"""Return an iterable of dictionary items where the values are always lists."""
for key, value in dct.items():
if value is None:
- value = []
- elif not isinstance(value, list):
- value = [value]
- yield key, value
+ list_of_values = []
+ elif isinstance(value, list):
+ list_of_values = value
+ else:
+ list_of_values = [value]
+ yield key, list_of_values
diff --git a/mex/common/types/email.py b/mex/common/types/email.py
index 3a98df1b..32128d7c 100644
--- a/mex/common/types/email.py
+++ b/mex/common/types/email.py
@@ -9,6 +9,8 @@
class Email(str):
"""Email address of a person, organization or other entity."""
+ __slots__ = ()
+
@classmethod
def __get_pydantic_core_schema__(
cls, source_type: Any, handler: GetCoreSchemaHandler
diff --git a/mex/common/types/identifier.py b/mex/common/types/identifier.py
index c2537dee..483793c3 100644
--- a/mex/common/types/identifier.py
+++ b/mex/common/types/identifier.py
@@ -12,6 +12,8 @@
class Identifier(str):
"""Common identifier class based on UUID version 4."""
+ __slots__ = ()
+
@classmethod
def generate(cls, seed: int | None = None) -> Self:
"""Generate a new identifier from a seed or random UUID version 4."""
diff --git a/mex/common/types/link.py b/mex/common/types/link.py
index 7ed49d54..0fefddeb 100644
--- a/mex/common/types/link.py
+++ b/mex/common/types/link.py
@@ -42,7 +42,8 @@ def validate_strings(cls, value: Any) -> dict[str, Any]:
return {"url": value}
if isinstance(value, dict):
return value
- raise ValueError(f"Allowed input types are dict and str, got {type(value)}")
+ msg = f"Allowed input types are dict and str, got {type(value)}"
+ raise ValueError(msg)
def __hash__(self) -> int:
"""Return the hash of this link."""
diff --git a/mex/common/types/path.py b/mex/common/types/path.py
index 6a1539d1..1dd93363 100644
--- a/mex/common/types/path.py
+++ b/mex/common/types/path.py
@@ -16,7 +16,7 @@ def __init__(self, path: Union[str, Path, "PathWrapper"]) -> None:
if isinstance(path, str):
path = Path(path)
elif isinstance(path, PathWrapper):
- path = path._path
+ path = path._path # noqa: SLF001
self._path = path
@classmethod
@@ -52,7 +52,8 @@ def __eq__(self, other: object) -> bool:
"""Return true for two PathWrappers with equal paths."""
if isinstance(other, PathWrapper):
return self._path.__eq__(other._path)
- raise TypeError(f"Can't compare {type(other)} with {type(self)}")
+ msg = f"Can't compare {type(other)} with {type(self)}"
+ raise TypeError(msg)
def is_absolute(self) -> bool:
"""True if the underlying path is absolute."""
diff --git a/mex/common/types/temporal_entity.py b/mex/common/types/temporal_entity.py
index 3f591db0..f116d9cf 100644
--- a/mex/common/types/temporal_entity.py
+++ b/mex/common/types/temporal_entity.py
@@ -59,6 +59,7 @@ class TemporalEntityPrecision(Enum):
YEAR_MONTH_DAY_TIME_REGEX = r"^[1-9]\d{3}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}Z$"
YEAR_MONTH_DAY_REGEX = r"^\d{4}-(0[1-9]|1[0-2])-(0[1-9]|[12][0-9]|3[01])$"
YEAR_MONTH_REGEX = r"^(?:\d{4}|(?:\d{4}-(?:0[1-9]|1[0-2])))$"
+MAX_DATETIME_ARGUMENTS = 7
@total_ordering
@@ -70,9 +71,7 @@ class TemporalEntity:
precision: TemporalEntityPrecision
date_time: datetime
STR_SCHEMA_PATTERN = TEMPORAL_ENTITY_REGEX
- ALLOWED_PRECISION_LEVELS = [
- key for key in TemporalEntityPrecision.__members__.values()
- ]
+ ALLOWED_PRECISION_LEVELS = list(TemporalEntityPrecision.__members__.values())
JSON_SCHEMA_CONFIG: dict[str, str | list[str]] = {
"examples": [
"2011",
@@ -98,7 +97,7 @@ def __init__(
tzinfo: tzinfo | None = None,
) -> None: ... # pragma: no cover
- def __init__(
+ def __init__( # noqa: PLR0912
self,
*args: Union[int, str, date, datetime, "TemporalEntity"],
precision: TemporalEntityPrecision | None = None,
@@ -123,18 +122,19 @@ def __init__(
TemporalEntity(2009, 9, 30, 23, 59, 5, tzinfo=timezone("CET"))
TemporalEntity(TemporalEntity(2000))
"""
- if len(args) > 7:
- raise TypeError(
- f"Temporal entity takes at most 7 arguments ({len(args)} given)"
+ if len(args) > MAX_DATETIME_ARGUMENTS:
+ msg = (
+ f"Temporal entity takes at most {MAX_DATETIME_ARGUMENTS} arguments "
+ f"({len(args)} given)"
)
+ raise TypeError(msg)
if len(args) == 1 and isinstance(
args[0], str | date | datetime | TemporalEntity
):
if tzinfo:
- raise TypeError(
- "Temporal entity does not accept tzinfo in parsing mode"
- )
+ msg = "Temporal entity does not accept tzinfo in parsing mode"
+ raise TypeError(msg)
if isinstance(args[0], TemporalEntity):
date_time, parsed_precision = self._parse_temporal_entity(args[0])
elif isinstance(args[0], datetime):
@@ -147,10 +147,11 @@ def __init__(
args = cast(tuple[int, ...], args)
date_time, parsed_precision = self._parse_integers(*args, tzinfo=tzinfo)
else:
- raise TypeError(
+ msg = (
"Temporal entity takes a single str, date, datetime or "
"TemporalEntity argument or up to 7 integers"
)
+ raise TypeError(msg)
if precision:
self._validate_precision(precision)
@@ -227,7 +228,7 @@ def _parse_integers(
if tzinfo is None:
tzinfo = CET
padded = tuple(a or d for a, d in zip_longest(args, (1970, 1, 1, 0, 0, 0, 0)))
- date_time = datetime(*padded, tzinfo=tzinfo) # type: ignore
+ date_time = datetime(*padded, tzinfo=tzinfo) # type: ignore[arg-type,misc]
precision = TEMPORAL_ENTITY_PRECISIONS_BY_ARG_LENGTH[len(args)]
return date_time, precision
@@ -267,12 +268,14 @@ def _parse_date(
value: date,
) -> tuple[datetime, TemporalEntityPrecision]:
"""Parse a date and assume the precision is days."""
- return datetime(value.year, value.month, value.day), TemporalEntityPrecision.DAY
+ return datetime(
+ value.year, value.month, value.day, tzinfo=CET
+ ), TemporalEntityPrecision.DAY
- def __eq__(self, other: Any) -> bool:
+ def __eq__(self, other: object) -> bool:
"""Return whether the given other value is the same as this one."""
try:
- other_temporal = TemporalEntity(other)
+ other_temporal = TemporalEntity(other) # type: ignore[call-overload]
except TypeError:
return False
return bool(
diff --git a/mex/common/types/text.py b/mex/common/types/text.py
index 14f55f8f..ad4965b9 100644
--- a/mex/common/types/text.py
+++ b/mex/common/types/text.py
@@ -52,7 +52,8 @@ def validate_strings(cls, value: Any) -> dict[str, Any]:
return {"value": value}
if isinstance(value, dict):
return value
- raise ValueError(f"Allowed input types are dict and str, got {type(value)}")
+ msg = f"Allowed input types are dict and str, got {type(value)}"
+ raise ValueError(msg)
def __hash__(self) -> int:
"""Return the hash of Text."""
diff --git a/mex/common/utils.py b/mex/common/utils.py
index 2638077f..c507d54d 100644
--- a/mex/common/utils.py
+++ b/mex/common/utils.py
@@ -25,10 +25,7 @@
def contains_any(base: Container[T], tokens: Iterable[T]) -> bool:
"""Check if a given base contains any of the given tokens."""
- for token in tokens:
- if token in base:
- return True
- return False
+ return any(token in base for token in tokens)
def any_contains_any(bases: Iterable[Container[T] | None], tokens: Iterable[T]) -> bool:
diff --git a/mex/common/wikidata/connector.py b/mex/common/wikidata/connector.py
index a055b744..42f7cce6 100644
--- a/mex/common/wikidata/connector.py
+++ b/mex/common/wikidata/connector.py
@@ -1,8 +1,11 @@
from functools import cache
+from typing import cast
from mex.common.connector.http import HTTPConnector
from mex.common.settings import BaseSettings
+_PROPS = "info|aliases|labels|descriptions|datatype|claims|sitelinks|sitelinks/urls"
+
class WikidataQueryServiceConnector(HTTPConnector):
"""Connector class to handle requesting the Wikidata Query Service."""
@@ -34,10 +37,8 @@ def get_data_by_query(self, query: str) -> list[dict[str, dict[str, str]]]:
"User-Agent": f"{settings.mex_web_user_agent}",
"Api-User-Agent": f"{settings.mex_web_user_agent}",
}
-
results = self.request("GET", params=params, headers=headers)
-
- return results["results"]["bindings"] # type: ignore
+ return cast(list[dict[str, dict[str, str]]], results["results"]["bindings"])
class WikidataAPIConnector(HTTPConnector):
@@ -69,18 +70,7 @@ def get_wikidata_item_details_by_id(self, item_id: str) -> dict[str, str]:
"action": "wbgetentities",
"format": "json",
"ids": item_id,
- "props": "|".join(
- [
- "info",
- "aliases",
- "labels",
- "descriptions",
- "datatype",
- "claims",
- "sitelinks",
- "sitelinks/urls",
- ]
- ),
+ "props": _PROPS,
"formatversion": "2",
}
headers = {
@@ -88,4 +78,4 @@ def get_wikidata_item_details_by_id(self, item_id: str) -> dict[str, str]:
"Api-User-Agent": f"{settings.mex_web_user_agent}",
}
results = self.request("GET", params=params, headers=headers)
- return results["entities"][item_id] # type: ignore
+ return cast(dict[str, str], results["entities"][item_id])
diff --git a/mex/common/wikidata/extract.py b/mex/common/wikidata/extract.py
index 1aa1e5ff..e60a560f 100644
--- a/mex/common/wikidata/extract.py
+++ b/mex/common/wikidata/extract.py
@@ -50,8 +50,9 @@ def search_organization_by_label(
try:
wd_item_id = results[0]["item"]["value"].split("/")[-1]
- except KeyError as exc:
- raise MExError(f"KeyError: Error processing results for {item_label}") from exc
+ except KeyError as error:
+ msg = f"KeyError: Error processing results for {item_label}"
+ raise MExError(msg) from error
return _get_organization_details(wd_item_id)
@@ -134,14 +135,12 @@ def search_organizations_by_label(
for item in results:
try:
wd_item_id = item["item"]["value"].split("/")[-1]
- except KeyError as exc:
- raise MExError(
- f"KeyError: Error processing results for {item_label}"
- ) from exc
- except IndexError as exc:
- raise MExError(
- f"IndexError: Error processing results for {item_label}"
- ) from exc
+ except KeyError as error:
+ msg = f"KeyError: Error processing results for {item_label}"
+ raise MExError(msg) from error
+ except IndexError as error:
+ msg = f"IndexError: Error processing results for {item_label}"
+ raise MExError(msg) from error
yield _get_organization_details(wd_item_id)
diff --git a/pdm.lock b/pdm.lock
index fcea341a..862a02cf 100644
--- a/pdm.lock
+++ b/pdm.lock
@@ -5,7 +5,7 @@
groups = ["default", "dev"]
strategy = ["inherit_metadata"]
lock_version = "4.5.0"
-content_hash = "sha256:5b087c16b56627dbf2610d4bfb4bfc424949852d2f4c4487ea9b3d02ed1a0e6e"
+content_hash = "sha256:e4266229127d28efe577af078ad22dd37650ba3323b215876c04fe81b42d87d3"
[[metadata.targets]]
requires_python = "==3.11.*"
diff --git a/pyproject.toml b/pyproject.toml
index 93b45aa1..0f22a4e8 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -13,17 +13,17 @@ dependencies = [
"langdetect>=1.0.9,<2",
"ldap3>=2.9.1,<3",
"mex-model@git+https://github.com/robert-koch-institut/mex-model.git@2.5.0",
- "numpy>=2.0.1,<3",
- "pandas>=2.2.2,<3",
+ "numpy>=2.1.2,<3",
+ "pandas>=2.2.3,<3",
"pyarrow>=17.0.0,<18",
- "pydantic-settings>=2.4.0,<3",
- "pydantic>=2.8.2,<3",
+ "pydantic-settings>=2.5.2,<3",
+ "pydantic>=2.9.2,<3",
"pytz>=2024.1,<2024.2",
"requests>=2.32.3,<3",
]
optional-dependencies.dev = [
"ipdb>=0.13.13,<1",
- "pandas-stubs>=2.2.2,<3",
+ "pandas-stubs>=2.2.3,<3",
"mypy>=1.11.2,<2",
"pytest-cov>=5.0.0,<6",
"pytest-random-order>=1.1.1,<2",
@@ -97,49 +97,57 @@ docstring-code-format = true
[tool.ruff.lint]
ignore = [
- "D100", # Allow missing module docstring for brevity
- "D104", # Allow missing package docstring for brevity
- "D106", # Allow missing nested class docstring (eg pydantic Config)
- "D203", # Disallow blank line before class docstring (inverse of D211)
- "D213", # Disallow multi-line docstring starting at second line (inverse of D212)
- "D406", # Allow section name ending with newline (google style compat)
- "D407", # Allow missing dashed underline after section (google style compat)
- "D413", # Allow missing blank line after last section (google style compat)
- "N805", # Allow first argument of a method to be non-self (pydantic compat)
- "N815", # Allow mixedCase variables in class scope (model compat)
- "RUF012", # Allow mutable class attributes (pydantic compat)
-]
-select = [
- "A", # Flake8 builtin shaddow
- "B", # BugBear bug and issue finder
- "C90", # McCabe complexity checker
- "D", # Python docstring style checker
- "E", # Python code style errors
- "ERA", # Commented-out code detector
- "F", # Pyflakes passive python checker
- "I", # Isort import utility
- "N", # Pep8 naming conventions
- "PERF", # Lint performance anti-patterns
- "RET", # Flake8 return statement checker
- "RUF", # Ruff-specific rules
- "S", # Bandit automated security testing
- "T10", # Flake8 debug statement checker
- "T20", # Flake8 print statement checker
- "UP", # PyUpgrade syntax recommender
- "W", # Python code style warnings
+ "AIR", # Disable airflow specific rules (we are not using airflow)
+ "ANN", # Disable all annotations checks (handled by mypy)
+ "COM", # Disable flake8-commas checks (let ruff format handle that)
+ "CPY", # Disable copyright notice checks (we have LICENSE files)
+ "D100", # Allow missing module docstring (for brevity and speed)
+ "D104", # Allow missing package docstring (for brevity and speed)
+ "D203", # Disallow blank line before class docstring (inverse of D211)
+ "D213", # Disallow multi-line docstring starting at second line (inverse of D212)
+ "D406", # Allow section name ending with newline (google style compat)
+ "D407", # Allow missing dashed underline after section (google style compat)
+ "D413", # Allow missing blank line after last section (google style compat)
+ "DJ", # Disable django specific checks (we are not using django)
+ "FBT", # Disable boolean type hint checks (for more flexibility)
+ "FIX", # Allow committing with open TODOs (don't punish committers)
+ "N805", # Allow first argument of a method to be non-self (pydantic compat)
+ "N815", # Allow mixedCase variables in class scope (model compat)
+ "PTH123", # Allow using builtin open method (simpler than pathlib)
+ "RUF012", # Allow mutable class attributes (pydantic compat)
+ "SIM108", # Allow explicit if-else instead of ternary (easier to read)
+ "TD003", # Allow TODOs without ticket link (don't punish TODO writers)
+ "TRY003", # Allow long exception message at the raise site (for pydantic)
]
+select = ["ALL"]
[tool.ruff.lint.per-file-ignores]
+"docs/**" = [
+ "INP001", # Docs do not need to be a package
+]
+"mex/common/testing/**" = [
+ "ARG001", # Allow unused function arguments for pytest plugin
+]
"tests/**" = [
- "D101", # Allow missing docstring in public class for tests
- "D102", # Allow missing docstring in public method for tests
- "D103", # Allow missing docstring in public function for tests
- "D107", # Allow missing docstring in `__init__` for tests
- "E501", # Allow line too long in tests
- "N807", # Allow mocking `__init__` for tests
- "S101", # Allow use of `assert` in tests
+ "ARG005", # Allow unused lambda arguments for mocking
+ "D101", # Allow missing docstring in public class
+ "D102", # Allow missing docstring in public method
+ "D103", # Allow missing docstring in public function
+ "D107", # Allow missing docstring in `__init__`
+ "E501", # Allow longer lines with test data
+ "ISC", # Allow implicitly concatenated strings
+ "N807", # Allow mocking `__init__`
+ "PLR0915", # Allow functions with many statements
+ "PLR2004", # Allow comparing with static values
+ "PT004", # Allow public fixtures without returns
+ "PT013", # Allow more flexible pytest imports
+ "S101", # Allow use of `assert` in tests
+ "SLF", # Allow private member access
]
+[tool.ruff.lint.flake8-import-conventions.extend-aliases]
+"reflex" = "rx"
+
[tool.ruff.lint.isort]
known-first-party = ["mex", "tests"]
diff --git a/tests/backend_api/conftest.py b/tests/backend_api/conftest.py
index 6096e441..e2be02de 100644
--- a/tests/backend_api/conftest.py
+++ b/tests/backend_api/conftest.py
@@ -6,7 +6,7 @@
from mex.common.backend_api.connector import BackendApiConnector
-@pytest.fixture()
+@pytest.fixture
def mocked_backend(monkeypatch: MonkeyPatch) -> MagicMock:
"""Return the mocked request dispatch method of backend connector."""
mocked_send_request = MagicMock(
diff --git a/tests/conftest.py b/tests/conftest.py
index 34573fe3..511a5189 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -64,7 +64,7 @@ def merged_person() -> MergedPerson:
)
-@pytest.fixture()
+@pytest.fixture
def rule_set_request() -> PersonRuleSetRequest:
"""Return a dummy person rule set request for testing purposes."""
return PersonRuleSetRequest(
@@ -74,7 +74,7 @@ def rule_set_request() -> PersonRuleSetRequest:
)
-@pytest.fixture()
+@pytest.fixture
def rule_set_response() -> PersonRuleSetResponse:
"""Return a dummy person rule set response for testing purposes."""
return PersonRuleSetResponse(
diff --git a/tests/identity/test_memory.py b/tests/identity/test_memory.py
index dad73272..41e10a4e 100644
--- a/tests/identity/test_memory.py
+++ b/tests/identity/test_memory.py
@@ -26,32 +26,32 @@ def test_assign() -> None:
new_identity = provider.assign(had_primary_source, identifier_in_primary_source)
- assert new_identity.model_dump() == dict(
- hadPrimarySource=had_primary_source,
- identifierInPrimarySource=identifier_in_primary_source,
- stableTargetId=Joker(),
- identifier=Joker(),
- )
+ assert new_identity.model_dump() == {
+ "hadPrimarySource": had_primary_source,
+ "identifierInPrimarySource": identifier_in_primary_source,
+ "stableTargetId": Joker(),
+ "identifier": Joker(),
+ }
found_identity = provider.assign(had_primary_source, identifier_in_primary_source)
- assert found_identity.model_dump() == dict(
- hadPrimarySource=had_primary_source,
- identifierInPrimarySource=identifier_in_primary_source,
- stableTargetId=new_identity.stableTargetId,
- identifier=new_identity.identifier,
- )
+ assert found_identity.model_dump() == {
+ "hadPrimarySource": had_primary_source,
+ "identifierInPrimarySource": identifier_in_primary_source,
+ "stableTargetId": new_identity.stableTargetId,
+ "identifier": new_identity.identifier,
+ }
provider.close()
provider = MemoryIdentityProvider.get()
fresh_identity = provider.assign(had_primary_source, identifier_in_primary_source)
- assert fresh_identity.model_dump() == dict(
- hadPrimarySource=had_primary_source,
- identifierInPrimarySource=identifier_in_primary_source,
- stableTargetId=new_identity.stableTargetId,
- identifier=new_identity.identifier,
- )
+ assert fresh_identity.model_dump() == {
+ "hadPrimarySource": had_primary_source,
+ "identifierInPrimarySource": identifier_in_primary_source,
+ "stableTargetId": new_identity.stableTargetId,
+ "identifier": new_identity.identifier,
+ }
def test_fetch_empty() -> None:
diff --git a/tests/ldap/conftest.py b/tests/ldap/conftest.py
index d137e03c..edea5fcb 100644
--- a/tests/ldap/conftest.py
+++ b/tests/ldap/conftest.py
@@ -12,43 +12,43 @@
LDAPMocker = Callable[[PagedSearchResults], None]
-SAMPLE_PERSON_ATTRS = dict(
- company=["RKI"],
- department=["XY"],
- departmentNumber=["XY2"],
- displayName=["Sample, Sam"],
- employeeID=["1024"],
- givenName=["Sam"],
- mail=["SampleS@mail.tld"],
- objectGUID=["{00000000-0000-4000-8000-000000000000}"],
- ou=["XY"],
- sAMAccountName=["SampleS"],
- sn=["Sample"],
-)
+SAMPLE_PERSON_ATTRS = {
+ "company": ["RKI"],
+ "department": ["XY"],
+ "departmentNumber": ["XY2"],
+ "displayName": ["Sample, Sam"],
+ "employeeID": ["1024"],
+ "givenName": ["Sam"],
+ "mail": ["SampleS@mail.tld"],
+ "objectGUID": ["{00000000-0000-4000-8000-000000000000}"],
+ "ou": ["XY"],
+ "sAMAccountName": ["SampleS"],
+ "sn": ["Sample"],
+}
-XY_DEPARTMENT_ATTRS = dict(
- mail=["XY@mail.tld"],
- objectGUID=["{00000000-0000-4000-8000-000000000042}"],
- sAMAccountName=["XY"],
-)
+XY_DEPARTMENT_ATTRS = {
+ "mail": ["XY@mail.tld"],
+ "objectGUID": ["{00000000-0000-4000-8000-000000000042}"],
+ "sAMAccountName": ["XY"],
+}
-XY2_DEPARTMENT_ATTRS = dict(
- mail=["XY2@mail.tld"],
- objectGUID=["{00000000-0000-4000-8000-000000000043}"],
- sAMAccountName=["XY2"],
-)
+XY2_DEPARTMENT_ATTRS = {
+ "mail": ["XY2@mail.tld"],
+ "objectGUID": ["{00000000-0000-4000-8000-000000000043}"],
+ "sAMAccountName": ["XY2"],
+}
-XY_FUNC_ACCOUNT_ATTRS = dict(
- mail=["XY@mail.tld"],
- objectGUID=["{00000000-0000-4000-8000-000000000044}"],
- sAMAccountName=["XY"],
-)
+XY_FUNC_ACCOUNT_ATTRS = {
+ "mail": ["XY@mail.tld"],
+ "objectGUID": ["{00000000-0000-4000-8000-000000000044}"],
+ "sAMAccountName": ["XY"],
+}
-XY2_FUNC_ACCOUNT_ATTRS = dict(
- mail=["XY2@mail.tld"],
- objectGUID=["{00000000-0000-4000-8000-000000000045}"],
- sAMAccountName=["XY2"],
-)
+XY2_FUNC_ACCOUNT_ATTRS = {
+ "mail": ["XY2@mail.tld"],
+ "objectGUID": ["{00000000-0000-4000-8000-000000000045}"],
+ "sAMAccountName": ["XY2"],
+}
@pytest.fixture
@@ -60,7 +60,7 @@ def __init__(self: LDAPConnector) -> None:
self._connection = MagicMock(spec=Connection, extend=Mock())
self._connection.extend.standard.paged_search = MagicMock(
side_effect=[
- [dict(attributes=e) for e in entries] for entries in results
+ [{"attributes": e} for e in entries] for entries in results
]
)
diff --git a/tests/models/test_base.py b/tests/models/test_base.py
index f008e28e..76b8994b 100644
--- a/tests/models/test_base.py
+++ b/tests/models/test_base.py
@@ -106,8 +106,8 @@ def test_base_model_listyness_fix(
) -> None:
try:
model = ComplexDummyModel.model_validate(data)
- except Exception as error:
- assert str(expected) in str(error)
+ except Exception as error: # noqa: BLE001
+ assert str(expected) in str(error) # noqa: PT017
else:
actual = model.model_dump()
for key, value in expected.items():
@@ -125,7 +125,7 @@ class Shelter(Pet):
with pytest.raises(
ValidationError, match="Input should be a valid dictionary or instance of Pet"
):
- Shelter(inhabitants="foo") # type: ignore
+ Shelter(inhabitants="foo") # type: ignore[call-arg]
class Computer(BaseModel):
diff --git a/tests/test_cli.py b/tests/test_cli.py
index 1385a417..7ade9a37 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -16,6 +16,8 @@
class MyStr(str):
"""Dummy string subclass for _field_to_option test."""
+ __slots__ = ()
+
class MyEnum(Enum):
"""Dummy enum class for _field_to_option test."""
@@ -110,7 +112,10 @@ class MyEnum(Enum):
create_model(
"OptionalFlagSettings",
__base__=BaseSettings,
- optional_flag=(bool, Field(False, description="This flag is optional")),
+ optional_flag=(
+ bool,
+ Field(default=False, description="This flag is optional"),
+ ),
),
{
"name": "optional_flag",
@@ -169,7 +174,7 @@ class MyEnum(Enum):
__base__=BaseSettings,
union_field=(
bool | str,
- Field(True, description="String or boolean"),
+ Field(default=True, description="String or boolean"),
),
),
{
diff --git a/tests/test_utils.py b/tests/test_utils.py
index aa3b047d..d379aea7 100644
--- a/tests/test_utils.py
+++ b/tests/test_utils.py
@@ -55,7 +55,7 @@ def test_any_contains_any(base: Any, tokens: Iterable[Any], expected: bool) -> N
@pytest.mark.parametrize(
("annotation", "types", "expected"),
- (
+ [
(None, [str], False),
(str, [str], True),
(str, [Identifier], False),
@@ -63,7 +63,7 @@ def test_any_contains_any(base: Any, tokens: Iterable[Any], expected: bool) -> N
(list[str | int | list[str]], [str, float], False),
(list[str | int | list[str]], [int, str], True),
(MergedPersonIdentifier | None, MERGED_IDENTIFIER_CLASSES, True),
- ),
+ ],
ids=[
"static None",
"simple str",
@@ -85,7 +85,7 @@ class DummyModel(BaseModel):
@pytest.mark.parametrize(
("annotation", "flags", "expected_types"),
- (
+ [
(str, {}, [str]),
(None, {}, [NoneType]),
(None, {"include_none": False}, []),
@@ -103,7 +103,7 @@ class DummyModel(BaseModel):
{"unpack_literal": False},
[Literal["okay"], NoneType],
),
- ),
+ ],
ids=[
"string",
"None allowing None",
@@ -141,7 +141,7 @@ class PseudoModel(BaseModel):
@pytest.mark.parametrize(
("string", "expected"),
- (("", ""), ("__XYZ__", "xyz"), ("/foo/BAR$42", "foo bar 42")),
+ [("", ""), ("__XYZ__", "xyz"), ("/foo/BAR$42", "foo bar 42")],
)
def test_normalize(string: str, expected: str) -> None:
assert normalize(string) == expected
diff --git a/tests/testing/test_joker.py b/tests/testing/test_joker.py
index 715fc40e..3af85287 100644
--- a/tests/testing/test_joker.py
+++ b/tests/testing/test_joker.py
@@ -2,7 +2,7 @@
def test_joker_eq() -> None:
- assert Joker() == None # noqa
+ assert Joker() == None # noqa: E711
assert Joker() == 1
assert {"foo": Joker()} == {"foo": ["bar", Joker()]}
diff --git a/tests/types/test_temporal_entity.py b/tests/types/test_temporal_entity.py
index 53d7dd42..978fc773 100644
--- a/tests/types/test_temporal_entity.py
+++ b/tests/types/test_temporal_entity.py
@@ -20,7 +20,7 @@
("args", "kwargs", "message"),
[
(
- (datetime.now(),),
+ (datetime.now(tz=UTC),),
{"tzinfo": UTC},
"Temporal entity does not accept tzinfo in parsing mode",
),
@@ -155,7 +155,7 @@ def test_temporal_entity_value_errors(
),
(
TemporalEntity,
- (datetime(2020, 3, 22, 14, 30, 58),),
+ (datetime(2020, 3, 22, 14, 30, 58, tzinfo=CET),),
{},
'TemporalEntity("2020-03-22T13:30:58Z")',
),
@@ -177,19 +177,19 @@ def test_temporal_entity_value_errors(
),
(
YearMonthDayTime,
- (YearMonthDayTime(2004, 11, 21, 19, 59, tzinfo=timezone("UTC")),),
+ (YearMonthDayTime(2004, 11, 21, 19, 59, tzinfo=UTC),),
{},
'YearMonthDayTime("2004-11-21T19:59:00Z")',
),
(
TemporalEntity,
- (datetime(2004, 11, 19, 00, 00),),
+ (datetime(2004, 11, 19, 00, 00, tzinfo=CET),),
{"precision": TemporalEntityPrecision.DAY},
'TemporalEntity("2004-11-19")',
),
(
YearMonth,
- (datetime(2004, 11, 19, 00, 00),),
+ (datetime(2004, 11, 19, 00, 00, tzinfo=CET),),
{"precision": TemporalEntityPrecision.YEAR},
'YearMonth("2004")',
),
@@ -226,8 +226,8 @@ def test_temporal_entity_eq() -> None:
assert TemporalEntity(2004) == TemporalEntity("2004")
assert TemporalEntity(2004, 11) == TemporalEntity(2004, 11)
assert TemporalEntity(2004, 11, 2) == "2004-11-02"
- assert TemporalEntity(2020, 3, 22, 14, 30, 58, 0) == datetime(
- 2020, 3, 22, 14, 30, 58, 0
+ assert TemporalEntity(2020, 3, 22, 14, 30, 58, 0, tzinfo=UTC) == datetime(
+ 2020, 3, 22, 14, 30, 58, 0, tzinfo=UTC
)
assert TemporalEntity(2005) != object()
@@ -236,7 +236,9 @@ def test_temporal_entity_gt() -> None:
assert TemporalEntity(2004) > TemporalEntity("2003")
assert TemporalEntity(2004, 11) < "2013-10-02"
assert TemporalEntity(2004, 11) <= TemporalEntity(2004, 12)
- assert TemporalEntity(2020, 3, 22, 14, 30, 58) >= datetime(2020, 3, 22, 14, 29)
+ assert TemporalEntity(2020, 3, 22, 14, 30, 58, tzinfo=UTC) >= datetime(
+ 2020, 3, 22, 14, 29, tzinfo=UTC
+ )
with pytest.raises(NotImplementedError):
assert TemporalEntity(2005) > object()