Apply isort

docs/conf.py

@@ -1,10 +1,9 @@
 import doctest
-
-import scitacean
-
 import os
 import sys
 
+import scitacean
+
 sys.path.insert(0, os.path.abspath("."))
 
 # General information about the project.

src/scitacean/__init__.py

@@ -9,12 +9,12 @@
 except importlib.metadata.PackageNotFoundError:
     __version__ = "0.0.0"
 
+from ._dataset_fields import DatasetType
 from .client import Client
 from .dataset import Dataset
 from .error import ScicatCommError, ScicatLoginError
 from .file import File
 from .pid import PID
-from ._dataset_fields import DatasetType
 
 __all__ = (
     "Client",

src/scitacean/_dataset_fields.py

@@ -11,7 +11,7 @@
 
 import dataclasses
 from datetime import datetime, timezone
-from typing import Any, Callable, Dict, Generator, Literal, List, Optional, Union
+from typing import Any, Callable, Dict, Generator, List, Literal, Optional, Union
 
 import dateutil.parser
 
@@ -88,7 +88,7 @@ def required(self, dataset_type: DatasetType) -> bool:
         ),
         Field(
             name="contact_email",
-            description="Email of contact person for this dataset. May contain a list of emails, which should then be seperated by semicolons.",
+            description="Email of contact person for this dataset. May contain a list of emails, which should then be separated by semicolons.",
             read_only=False,
             required_by_derived=True,
             required_by_raw=True,
@@ -328,7 +328,7 @@ def required(self, dataset_type: DatasetType) -> bool:
         ),
         Field(
             name="owner",
-            description="Owner or custodian of the dataset, usually first name + lastname. The string may contain a list of persons, which should then be seperated by semicolons.",
+            description="Owner or custodian of the dataset, usually first name + lastname. The string may contain a list of persons, which should then be separated by semicolons.",
             read_only=False,
             required_by_derived=True,
             required_by_raw=True,
@@ -338,7 +338,7 @@ def required(self, dataset_type: DatasetType) -> bool:
         ),
         Field(
             name="owner_email",
-            description="Email of owner or of custodian of the dataset. The string may contain a list of emails, which should then be seperated by semicolons.",
+            description="Email of owner or of custodian of the dataset. The string may contain a list of emails, which should then be separated by semicolons.",
             read_only=False,
             required_by_derived=False,
             required_by_raw=False,
@@ -628,7 +628,7 @@ def classification(self, val: Optional[str]):
 
     @property
     def contact_email(self) -> Optional[str]:
-        """Email of contact person for this dataset. May contain a list of emails, which should then be seperated by semicolons."""
+        """Email of contact person for this dataset. May contain a list of emails, which should then be separated by semicolons."""
         return self._fields["contact_email"]
 
     @contact_email.setter
@@ -800,7 +800,7 @@ def orcid_of_owner(self, val: Optional[str]):
 
     @property
     def owner(self) -> Optional[str]:
-        """Owner or custodian of the dataset, usually first name + lastname. The string may contain a list of persons, which should then be seperated by semicolons."""
+        """Owner or custodian of the dataset, usually first name + lastname. The string may contain a list of persons, which should then be separated by semicolons."""
         return self._fields["owner"]
 
     @owner.setter
@@ -809,7 +809,7 @@ def owner(self, val: Optional[str]):
 
     @property
     def owner_email(self) -> Optional[str]:
-        """Email of owner or of custodian of the dataset. The string may contain a list of emails, which should then be seperated by semicolons."""
+        """Email of owner or of custodian of the dataset. The string may contain a list of emails, which should then be separated by semicolons."""
         return self._fields["owner_email"]
 
     @owner_email.setter

src/scitacean/client.py

@@ -12,13 +12,13 @@
 
 import requests
 
+from . import model
 from .dataset import Dataset
 from .error import ScicatCommError, ScicatLoginError
 from .logging import get_logger
 from .pid import PID
 from .typing import FileTransfer
 from .util.credentials import SecretStr, StrStorage
-from . import model
 
 
 class Client:
@@ -532,7 +532,7 @@ def _get_token(url: str, username: StrStorage, password: StrStorage) -> str:
     # Users/login only works for functional accounts and auth/msad for regular users.
     # Try both and see what works. This is not nice but seems to be the only
     # feasible solution right now.
-    get_logger().info("Loging in to %s", url)
+    get_logger().info("Logging in to %s", url)
 
     response = _log_in_via_users_login(url=url, username=username, password=password)
     if response.ok:

src/scitacean/dataset.py

@@ -4,9 +4,10 @@
 """Main dataset structure."""
 
 from __future__ import annotations
+
+import html
 from dataclasses import dataclass
 from datetime import datetime
-import html
 from pathlib import Path
 from typing import Any, Dict, Iterable, List, Optional, Union
 

src/scitacean/file.py

@@ -4,13 +4,13 @@
 """Class to represent files."""
 
 from __future__ import annotations
-from datetime import datetime, timezone
+
 import hashlib
 import os
+from datetime import datetime, timezone
 from pathlib import Path, PurePosixPath
 from typing import Optional, Union
 
-
 from .error import IntegrityError
 from .logging import get_logger
 from .model import DataFile
@@ -66,7 +66,7 @@ def from_local(
             -> remote_path:            folder/file.nxs
             -> actual remote location: remote/storage/folder/file.nxs
 
-        ``remote_path`` can also be overriden, in which case ``path`` and
+        ``remote_path`` can also be overridden, in which case ``path`` and
         ``base_path`` are not used to deduce the "actual remote location".
 
         Parameters
@@ -250,7 +250,7 @@ def _new_hash(algorithm: str):
         return hashlib.new(algorithm)
 
 
-# size based on http://git.savannah.gnu.org/gitweb/?p=coreutils.git;a=blob;f=src/ioblksize.h;h=ed2f4a9c4d77462f357353eb73ee4306c28b37f1;hb=HEAD#l23  # noqa
+# size based on http://git.savannah.gnu.org/gitweb/?p=coreutils.git;a=blob;f=src/ioblksize.h;h=ed2f4a9c4d77462f357353eb73ee4306c28b37f1;hb=HEAD#l23  # noqa: E501
 def checksum_of_file(path: Union[str, Path], *, algorithm: str) -> str:
     chk = _new_hash(algorithm)
     buffer = memoryview(bytearray(128 * 1024))

src/scitacean/model.py

@@ -9,8 +9,8 @@
 
 """Pydantic models to encode data for communication with SciCat."""
 
-from datetime import datetime
 import enum
+from datetime import datetime
 from typing import Dict, List, Optional
 
 import pydantic

src/scitacean/pid.py

@@ -2,8 +2,9 @@
 # Copyright (c) 2022 Scitacean contributors (https://github.com/SciCatProject/scitacean)
 # @author Jan-Lukas Wynen
 from __future__ import annotations
-from typing import Optional
+
 import uuid
+from typing import Optional
 
 
 class PID:

src/scitacean/testing/client.py

@@ -6,18 +6,18 @@
 from __future__ import annotations
 
 import functools
+import uuid
 from copy import deepcopy
 from pathlib import Path
 from typing import Dict, List, Optional, Union
-import uuid
 
+from .. import model
 from ..client import Client, ScicatClient
 from ..dataset import Dataset
 from ..error import ScicatCommError
 from ..pid import PID
 from ..typing import FileTransfer
 from ..util.credentials import StrStorage
-from .. import model
 
 
 def _conditionally_disabled(func):
@@ -121,7 +121,7 @@ def __init__(
         """
         # Normally, client must not be None, but the fake must never
         # call it, so setting it to None serves as an extra safeguard.
-        super().__init__(client=None, file_transfer=file_transfer)  # noqa
+        super().__init__(client=None, file_transfer=file_transfer)  # type: ignore
 
         self._scicat_client = FakeScicatClient(self)
         self.disabled = {} if disable is None else dict(disable)
@@ -206,7 +206,7 @@ class FakeScicatClient(ScicatClient):
     """Mimics a ScicatClient, to be used by FakeClient."""
 
     def __init__(self, main_client):
-        super().__init__(url="", token="")  # noqa # nosec
+        super().__init__(url="", token="")  # nosec: B106
         self.main = main_client
 
     @_conditionally_disabled

src/scitacean/testing/docs.py

@@ -6,9 +6,9 @@
 
 from dateutil.parser import parse as parse_date
 
+from ..model import DataFile, DatasetType, OrigDatablock, RawDataset
 from ..pid import PID
 from .client import FakeClient
-from ..model import DataFile, DatasetType, OrigDatablock, RawDataset
 from .transfer import FakeFileTransfer
 
 

src/scitacean/testing/strategies.py

@@ -4,11 +4,12 @@
 from functools import partial
 from typing import Dict, Optional
 
-from email_validator import validate_email, EmailNotValidError
-from scitacean import Dataset, DatasetType, PID
-from scitacean._internal.orcid import orcid_checksum
+from email_validator import EmailNotValidError, validate_email
 from hypothesis import strategies as st
 
+from scitacean import PID, Dataset, DatasetType
+from scitacean._internal.orcid import orcid_checksum
+
 
 # email_validator and by extension pydantic is more picky than hypothesis
 # so make sure that generated emails actually pass model validation.

src/scitacean/testing/transfer.py

@@ -1,8 +1,8 @@
 # SPDX-License-Identifier: BSD-3-Clause
 # Copyright (c) 2022 Scitacean contributors (https://github.com/SciCatProject/scitacean)
 # @author Jan-Lukas Wynen
-from contextlib import contextmanager
 import os
+from contextlib import contextmanager
 from pathlib import Path
 from typing import Any, Dict, Optional, Union
 

src/scitacean/transfer/ess.py

@@ -2,11 +2,11 @@
 # Copyright (c) 2022 Scitacean contributors (https://github.com/SciCatProject/scitacean)
 # @author Jan-Lukas Wynen
 
+import os
 from contextlib import contextmanager
 from getpass import getpass
-import os
 from pathlib import Path
-from typing import Union, Tuple, Optional
+from typing import Optional, Tuple, Union
 
 # These are quite heavy dependencies.
 # It would be great if we could do without them in the long run.

src/scitacean/util/credentials.py

@@ -3,6 +3,7 @@
 # @author Jan-Lukas Wynen
 """Tools for securely handling credentials."""
 from __future__ import annotations
+
 import datetime
 from typing import Optional, Union
 

tests/client_test.py

@@ -1,17 +1,16 @@
 # SPDX-License-Identifier: BSD-3-Clause
 # Copyright (c) 2022 Scitacean contributors (https://github.com/SciCatProject/scitacean)
 # @author Jan-Lukas Wynen
-from copy import deepcopy
 import pickle
+from copy import deepcopy
 
-from dateutil.parser import parse as parse_date
 import pytest
-from scitacean.model import DataFile, DatasetType, DerivedDataset, OrigDatablock
-from scitacean import PID, ScicatCommError
+from dateutil.parser import parse as parse_date
 
+from scitacean import PID, Client, ScicatCommError
+from scitacean.model import DataFile, DatasetType, DerivedDataset, OrigDatablock
 from scitacean.testing.client import FakeClient
 from scitacean.util.credentials import SecretStr
-from scitacean import Client
 
 from . import data
 from .common.backend import skip_if_not_backend

tests/common/backend.py

@@ -1,16 +1,15 @@
 import json
-from pathlib import Path
-import requests
 import shutil
 import subprocess
 import time
+from pathlib import Path
 from urllib.parse import urljoin
 
 import pytest
+import requests
 
 from ..data import load_datasets, load_orig_datablocks
 
-
 _TEST_BASE = Path(__file__).resolve().parent.parent
 _SCICAT_DOCKER_CONFIG = _TEST_BASE / "scicatlive/docker-compose.yaml"
 _SCICAT_DATASET_SEED_FILE = Path("seed_db/seed/Dataset.json")

tests/common/files.py

@@ -2,8 +2,8 @@
 # Copyright (c) 2022 Scitacean contributors (https://github.com/SciCatProject/scitacean)
 # @author Jan-Lukas Wynen
 
-from datetime import datetime, timezone
 import hashlib
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import Any, Dict, Optional, Union
 

tests/conftest.py

@@ -1,13 +1,12 @@
-from dataclasses import dataclass
 import tempfile
+from dataclasses import dataclass
 from typing import Dict
 
 import hypothesis
 import pytest
 
 from .common import backend
 
-
 # The datasets strategy requires a large amount of memory and time.
 # This is not good but hard to avoid.
 # So simply disable health checks and accept that tests are slow.

tests/data/__init__.py

@@ -2,13 +2,12 @@
 # Copyright (c) 2022 Scitacean contributors (https://github.com/SciCatProject/scitacean)
 # @author Jan-Lukas Wynen
 """Handle input data for tests."""
-from functools import lru_cache
 import json
+from functools import lru_cache
 from pathlib import Path
 
 from scitacean.model import DerivedDataset, OrigDatablock, RawDataset
 
-
 _BASE_PATH = Path(__file__).resolve().parent
 
 

tests/dataset_fields_test.py

@@ -10,11 +10,13 @@
 from datetime import datetime, timedelta, timezone
 
 import dateutil.parser
-from hypothesis import given, settings, strategies as st
 import pydantic
 import pytest
-from scitacean.model import DataFile, DerivedDataset, OrigDatablock, RawDataset
+from hypothesis import given, settings
+from hypothesis import strategies as st
+
 from scitacean import Dataset, DatasetType
+from scitacean.model import DataFile, DerivedDataset, OrigDatablock, RawDataset
 
 
 def test_init_dataset_with_only_type():
@@ -32,12 +34,12 @@ def test_init_dataset_accepted_types(typ):
 
 def test_init_dataset_raises_for_bad_type():
     with pytest.raises(ValueError):
-        Dataset(type="bad-type")  # noqa
+        Dataset(type="bad-type")  # type: ignore
 
 
 def test_init_dataset_needs_type():
     with pytest.raises(TypeError):
-        Dataset()  # noqa
+        Dataset()  # type: ignore
 
 
 def test_init_dataset_sets_creation_time():