diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 51fc70b908332e03c8357bfc19df0d372f3359f7..dab142c89c067df7af00866d4ab34b0ceb12d5ac 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -1,12 +1,4 @@
repos:
- - repo: https://github.com/pycqa/flake8
- rev: 3.9.2
- hooks:
- - id: flake8
- additional_dependencies:
- - 'flake8-copyright==0.2.2'
- - 'flake8-debugger==3.1.0'
- - 'flake8-quotes==3.3.2'
- repo: https://github.com/astral-sh/ruff-pre-commit
# Ruff version.
rev: v0.3.7
diff --git a/arkindex/documents/api/ml.py b/arkindex/documents/api/ml.py
index 7e852fc139f2d1994194ea2d8922a54339086387..62fea8eafadde3a1533eaa67dff9d57804c4374f 100644
--- a/arkindex/documents/api/ml.py
+++ b/arkindex/documents/api/ml.py
@@ -440,7 +440,7 @@ class ManageClassificationsSelection(SelectionMixin, CorpusACLMixin, CreateAPIVi
mode = serializer.validated_data["mode"]
if mode == ClassificationMode.Create:
return self.create(corpus, request, *args, **kwargs)
- elif mode == ClassificationMode.Validate:
+ if mode == ClassificationMode.Validate:
elements = self.get_selection(corpus.id)
Classification.objects.filter(
element__in=elements,
diff --git a/arkindex/documents/dates.py b/arkindex/documents/dates.py
index 10643931a25ef85ddc16eacf9fbb9c262278d8ef..dc3012bef8a3276bb890e8cb6bb5607c5876e52d 100644
--- a/arkindex/documents/dates.py
+++ b/arkindex/documents/dates.py
@@ -45,7 +45,7 @@ class InterpretedDate(object):
"""
if self.month and self.day:
return DatePrecision.Day
- elif self.month:
+ if self.month:
return DatePrecision.Month
return DatePrecision.Year
diff --git a/arkindex/documents/serializers/elements.py b/arkindex/documents/serializers/elements.py
index 7c7099022611581f7974ae4d89934bd158c6a8b8..d8ba836bed4af52fe35ef1d7c072fe6d0f890914 100644
--- a/arkindex/documents/serializers/elements.py
+++ b/arkindex/documents/serializers/elements.py
@@ -667,8 +667,7 @@ class ElementSerializer(ElementTinySerializer):
validated_data.update(image=image, polygon=polygon)
- instance = super().update(instance, validated_data)
- return instance
+ return super().update(instance, validated_data)
class ElementNeighborsSerializer(serializers.ModelSerializer):
diff --git a/arkindex/documents/serializers/entities.py b/arkindex/documents/serializers/entities.py
index 1f107ee06bb5b60bbaee32debebaca28c2ec0be6..335e63e4504687c55a21fd278e4e9c4f108107ec 100644
--- a/arkindex/documents/serializers/entities.py
+++ b/arkindex/documents/serializers/entities.py
@@ -32,8 +32,7 @@ class EntityTypeSerializer(serializers.ModelSerializer):
corpus = data.get("corpus")
if self.instance and corpus:
raise ValidationError({"corpus": ["It is not possible to update an Entity Type's corpus."]})
- data = super().to_internal_value(data)
- return data
+ return super().to_internal_value(data)
def validate(self, data):
name = data.get("name") if "name" in data else self.instance.name
diff --git a/arkindex/documents/tasks.py b/arkindex/documents/tasks.py
index 2dd9855b9ba7fb4d9400db8973c18d6046354de1..1c42b0d360adf1e7e7f2c97f61f911629cfbedea 100644
--- a/arkindex/documents/tasks.py
+++ b/arkindex/documents/tasks.py
@@ -21,7 +21,7 @@ from arkindex.documents.models import (
Transcription,
TranscriptionEntity,
)
-from arkindex.ponos.models import Task
+from arkindex.ponos.models import Artifact, Task
from arkindex.process.models import Process, ProcessDatasetSet, ProcessElement, WorkerActivity, WorkerRun
from arkindex.training.models import DatasetElement, DatasetSet
from arkindex.users.models import User
@@ -41,6 +41,10 @@ def corpus_delete(corpus_id: str) -> None:
corpus.top_level_type_id = None
corpus.save(update_fields=["top_level_type_id"])
+ # Set process.element to NULL in all processes, to avoid IntegrityErrors when deleting elements, as
+ # elements are deleted before processes.
+ Process.objects.filter(corpus_id=corpus_id).exclude(element_id=None).update(element_id=None)
+
# Delete all related objects, bypassing RESTRICTs deletion rules
# and Django's way of loading everything into memory before deleting.
querysets = [
@@ -67,6 +71,8 @@ def corpus_delete(corpus_id: str) -> None:
Selection.objects.filter(element__corpus_id=corpus_id),
corpus.memberships.all(),
corpus.exports.all(),
+ # Delete task artifacts
+ Artifact.objects.filter(task__process__corpus_id=corpus_id),
# ProcessDatasetSet M2M
ProcessDatasetSet.objects.filter(set__dataset__corpus_id=corpus_id),
ProcessDatasetSet.objects.filter(process__corpus_id=corpus_id),
diff --git a/arkindex/documents/tests/test_edit_elementpath.py b/arkindex/documents/tests/test_edit_elementpath.py
index 21455699fdda5f61a5825ea0652c32827f92db3a..ac0f945e98d688a1481e61d08693a88beb374a00 100644
--- a/arkindex/documents/tests/test_edit_elementpath.py
+++ b/arkindex/documents/tests/test_edit_elementpath.py
@@ -363,7 +363,7 @@ class TestEditElementPath(FixtureTestCase):
path_id = elements["B"].paths.get().id
if path1.id == path_id:
return str(path1.path[0])
- elif path2.id == path_id:
+ if path2.id == path_id:
return str(path2.path[0])
raise AssertionError("Unexpected top-level path ID")
diff --git a/arkindex/images/managers.py b/arkindex/images/managers.py
index d3d97692560fdda9ab318a43b21e20e53f387d0b..61ffb364bbc729af6b505c277a08e00f33564dd0 100644
--- a/arkindex/images/managers.py
+++ b/arkindex/images/managers.py
@@ -47,7 +47,7 @@ class ImageServerManager(models.Manager):
f'The URL "{url}" does not match any existing image server. '
"Please ask an instance administrator to register the IIIF server for this image."
)
- elif servers_count > 1:
+ if servers_count > 1:
raise self.model.MultipleObjectsReturned(
f'The URL "{url}" matched multiple existing image servers'
)
diff --git a/arkindex/images/models.py b/arkindex/images/models.py
index aecc25fca690b179e55696ab1f9775179b18d830..8b904acaf919c199d8ce862d12280b5da03dd7f4 100644
--- a/arkindex/images/models.py
+++ b/arkindex/images/models.py
@@ -108,7 +108,7 @@ class ImageServer(models.Model):
src_url, dest_url = map(urllib.parse.urlsplit, (self.url, other.url))
if src_url.scheme != dest_url.scheme:
raise ValueError("Cannot merge into an image server of a different protocol")
- elif src_url.netloc != dest_url.netloc:
+ if src_url.netloc != dest_url.netloc:
raise ValueError("Cannot merge into an image server on a different domain")
# Check paths
diff --git a/arkindex/images/serializers.py b/arkindex/images/serializers.py
index 1b0805674f253a082a593f45c4438c27bdbb117a..bef4751cb1b59b42e96c76741ea2ea831731d74a 100644
--- a/arkindex/images/serializers.py
+++ b/arkindex/images/serializers.py
@@ -68,7 +68,7 @@ class ImageSerializer(serializers.ModelSerializer):
if not self.instance:
# Force the Unchecked status when creating a new image
return S3FileStatus.Unchecked
- elif value == S3FileStatus.Checked:
+ if value == S3FileStatus.Checked:
# Perform image validation if we are updating an existing image to Checked
try:
if self.instance.server.s3_bucket and not self.instance.server.s3_read_only_bucket:
diff --git a/arkindex/process/api.py b/arkindex/process/api.py
index e6c154ea70b51eee6455c9749ce2bd5243a23205..f527305661111a9e60b334b52f2e63ccaed632c4 100644
--- a/arkindex/process/api.py
+++ b/arkindex/process/api.py
@@ -402,8 +402,9 @@ class ProcessDetails(ProcessACLMixin, ProcessQuerysetMixin, RetrieveUpdateDestro
class ProcessRetry(ProcessACLMixin, ProcessQuerysetMixin, GenericAPIView):
- """
- Retry a process. Can only be used on processes with Error, Failed, Stopped or Completed states.\n\n
+ r"""
+ Retry a process. Can only be used on processes with Error, Failed, Stopped or Completed states.
+
Requires an **admin** access to the process and **guest** access to the process' farm.
"""
permission_classes = (IsVerified, )
@@ -427,9 +428,9 @@ class ProcessRetry(ProcessACLMixin, ProcessQuerysetMixin, GenericAPIView):
# Allow 'retrying' a process that has no Ponos tasks (that has never been started)
if len(process.tasks.all()) and state in (State.Unscheduled, State.Pending):
raise ValidationError({"__all__": ["This process is already pending"]})
- elif state == State.Running:
+ if state == State.Running:
raise ValidationError({"__all__": ["This process is already running"]})
- elif state == State.Stopping:
+ if state == State.Stopping:
raise ValidationError({"__all__": ["This process is stopping"]})
@extend_schema(
@@ -476,8 +477,9 @@ class FilesProcess(CreateAPIView):
)
)
class CorpusProcess(SelectionMixin, CorpusACLMixin, CreateAPIView):
- """
- Create a distributed process from elements of an Arkindex corpus.\n\n
+ r"""
+ Create a distributed process from elements of an Arkindex corpus.
+
Requires an **admin** access to the corpus.
"""
permission_classes = (IsVerified, )
@@ -542,8 +544,9 @@ class CorpusProcess(SelectionMixin, CorpusACLMixin, CreateAPIView):
),
)
class StartProcess(CorpusACLMixin, CreateAPIView):
- """
- Start a process, used to build a Workflow with Workers.\n\n
+ r"""
+ Start a process, used to build a Workflow with Workers.
+
Requires an **admin** access to the corpus of this process.
"""
permission_classes = (IsVerified, )
@@ -1555,8 +1558,9 @@ class WorkerRunDetails(ProcessACLMixin, RetrieveUpdateDestroyAPIView):
tags=["process"]
))
class ListProcessElements(CorpusACLMixin, ListAPIView):
- """
- List all elements for a process with workers.\n\n
+ r"""
+ List all elements for a process with workers.
+
Requires an **admin** access to the process corpus.
"""
pagination_class = CountCursorPagination
@@ -1579,8 +1583,7 @@ class ListProcessElements(CorpusACLMixin, ListAPIView):
def get_serializer_class(self):
if self.with_image:
return ProcessElementSerializer
- else:
- return ProcessElementLightSerializer
+ return ProcessElementLightSerializer
def get_queryset(self):
if not self.has_admin_access(self.process.corpus):
@@ -1829,8 +1832,9 @@ class WorkerActivityBase(ListAPIView):
)
)
class CorpusWorkersActivity(CorpusACLMixin, WorkerActivityBase):
- """
- Retrieve corpus wise statistics about the activity of all its worker processes.\n
+ r"""
+ Retrieve corpus wise statistics about the activity of all its worker processes.
+
Requires a **guest** access.
"""
@@ -1846,8 +1850,9 @@ class CorpusWorkersActivity(CorpusACLMixin, WorkerActivityBase):
)
)
class ProcessWorkersActivity(ProcessACLMixin, WorkerActivityBase):
- """
- Retrieve process statistics about the activity of its workers.\n
+ r"""
+ Retrieve process statistics about the activity of its workers.
+
Requires a **guest** access.
"""
diff --git a/arkindex/process/models.py b/arkindex/process/models.py
index 94d041202912e84b7f43ced2a9b347311fd3936d..8e8dff5625624eb63d18d28b6c3644ac7f529396 100644
--- a/arkindex/process/models.py
+++ b/arkindex/process/models.py
@@ -232,8 +232,7 @@ class Process(IndexableModel):
"""
if self.has_prefetched_tasks:
return max((t.expiry for t in self.tasks.all()), default=None)
- else:
- return self.tasks.aggregate(models.Max("expiry"))["expiry__max"]
+ return self.tasks.aggregate(models.Max("expiry"))["expiry__max"]
def get_last_run(self) -> int:
"""
diff --git a/arkindex/process/serializers/imports.py b/arkindex/process/serializers/imports.py
index 2e01179db67c303ef789998bd1e7ece990400e3e..23e601754682282d108caba5b82ca3d5cea3180f 100644
--- a/arkindex/process/serializers/imports.py
+++ b/arkindex/process/serializers/imports.py
@@ -545,7 +545,7 @@ class ApplyProcessTemplateSerializer(ProcessACLMixin, serializers.Serializer):
access_level = self.process_access_level(process)
if not access_level:
raise ValidationError(detail="Process with this ID does not exist.")
- elif access_level < Role.Contributor.value:
+ if access_level < Role.Contributor.value:
raise PermissionDenied(detail="You do not have a contributor access to this process.")
errors = []
@@ -627,7 +627,7 @@ class CorpusProcessSerializer(serializers.Serializer):
access_level = get_max_level(self.context["request"].user, corpus)
if not access_level:
raise ValidationError(["Corpus with this ID does not exist."])
- elif access_level < Role.Admin.value:
+ if access_level < Role.Admin.value:
raise ValidationError(["You do not have an admin access to this corpus."])
return corpus
diff --git a/arkindex/project/argparse.py b/arkindex/project/argparse.py
index 7f0f9330c6149fb6eed315e4cfc71114ebb40612..bbb3dcf17ccbee051c11c0c33d2236d32bde414a 100644
--- a/arkindex/project/argparse.py
+++ b/arkindex/project/argparse.py
@@ -37,8 +37,7 @@ class ModelArgument(object):
text_filter = {f"{self.text_search_field}__{self.text_search_lookup}": arg}
if self.many:
return qs.filter(**text_filter)
- else:
- return qs.get(**text_filter)
+ return qs.get(**text_filter)
class CorpusArgument(ModelArgument):
diff --git a/arkindex/project/serializer_fields.py b/arkindex/project/serializer_fields.py
index 230bafd37351cccedda4d2f0c8298f0b3cc1f916..06245b86fc0ef12f757846b56b71927b684d87bd 100644
--- a/arkindex/project/serializer_fields.py
+++ b/arkindex/project/serializer_fields.py
@@ -304,4 +304,4 @@ class NullField(serializers.CharField):
def to_internal_value(self, data):
if data is not None:
self.fail("invalid")
- return None
+ return
diff --git a/arkindex/project/tests/test_config.py b/arkindex/project/tests/test_config.py
index 4a046d010a6a6bfb00dfdc75ed1834b50513f058..ec9eb25440b9849e783bcf195a093c414006cdcd 100644
--- a/arkindex/project/tests/test_config.py
+++ b/arkindex/project/tests/test_config.py
@@ -26,7 +26,7 @@ class TestConfig(TestCase):
data = data.value
if data is None:
return self.represent_none(data)
- elif isinstance(data, (bool, int, float, bytes, str)):
+ if isinstance(data, (bool, int, float, bytes, str)):
return self.represent_data(data)
return self.represent_str(str(data))
diff --git a/arkindex/sql_validation/corpus_delete.sql b/arkindex/sql_validation/corpus_delete.sql
index 2ebb6b6f75be165e6be9d6bac416a10ec36d74bc..51eae442a74c5aba4fc8c8f7c0e9238bbe0dda90 100644
--- a/arkindex/sql_validation/corpus_delete.sql
+++ b/arkindex/sql_validation/corpus_delete.sql
@@ -10,6 +10,11 @@ FROM "documents_corpus"
WHERE "documents_corpus"."id" = '{corpus_id}'::uuid
LIMIT 21;
+UPDATE "process_process"
+SET "element_id" = NULL
+WHERE ("process_process"."corpus_id" = '{corpus_id}'::uuid
+ AND NOT ("process_process"."element_id" IS NULL));
+
SELECT "django_content_type"."id",
"django_content_type"."app_label",
"django_content_type"."model"
@@ -152,6 +157,15 @@ DELETE
FROM "documents_corpusexport"
WHERE "documents_corpusexport"."corpus_id" = '{corpus_id}'::uuid;
+DELETE
+FROM "ponos_artifact"
+WHERE "ponos_artifact"."id" IN
+ (SELECT U0."id"
+ FROM "ponos_artifact" U0
+ INNER JOIN "ponos_task" U1 ON (U0."task_id" = U1."id")
+ INNER JOIN "process_process" U2 ON (U1."process_id" = U2."id")
+ WHERE U2."corpus_id" = '{corpus_id}'::uuid);
+
DELETE
FROM "process_processdatasetset"
WHERE "process_processdatasetset"."id" IN
diff --git a/arkindex/sql_validation/corpus_delete_top_level_type.sql b/arkindex/sql_validation/corpus_delete_top_level_type.sql
index 80ae4c77e85a44b11f33a3ef17803d55a9fc6d7b..0a552ec5f429f0caa12f106c13e223d7afbe11ab 100644
--- a/arkindex/sql_validation/corpus_delete_top_level_type.sql
+++ b/arkindex/sql_validation/corpus_delete_top_level_type.sql
@@ -14,6 +14,11 @@ UPDATE "documents_corpus"
SET "top_level_type_id" = NULL
WHERE "documents_corpus"."id" = '{corpus_id}'::uuid;
+UPDATE "process_process"
+SET "element_id" = NULL
+WHERE ("process_process"."corpus_id" = '{corpus_id}'::uuid
+ AND NOT ("process_process"."element_id" IS NULL));
+
SELECT "django_content_type"."id",
"django_content_type"."app_label",
"django_content_type"."model"
@@ -156,6 +161,15 @@ DELETE
FROM "documents_corpusexport"
WHERE "documents_corpusexport"."corpus_id" = '{corpus_id}'::uuid;
+DELETE
+FROM "ponos_artifact"
+WHERE "ponos_artifact"."id" IN
+ (SELECT U0."id"
+ FROM "ponos_artifact" U0
+ INNER JOIN "ponos_task" U1 ON (U0."task_id" = U1."id")
+ INNER JOIN "process_process" U2 ON (U1."process_id" = U2."id")
+ WHERE U2."corpus_id" = '{corpus_id}'::uuid);
+
DELETE
FROM "process_processdatasetset"
WHERE "process_processdatasetset"."id" IN
diff --git a/arkindex/training/admin.py b/arkindex/training/admin.py
index f8cc278929d0c29dd3f53a18fd10a91aab19d5b6..c3c6c7a8b5362278dfac8165e183eadc04a8938b 100644
--- a/arkindex/training/admin.py
+++ b/arkindex/training/admin.py
@@ -48,8 +48,7 @@ class DatasetAdmin(admin.ModelAdmin):
self.readonly_fields = self.__class__.readonly_fields
if obj is not None:
self.readonly_fields += ("unique_elements",)
- form = super().get_form(request, obj=None, **kwargs)
- return form
+ return super().get_form(request, obj=None, **kwargs)
admin.site.register(Model, ModelAdmin)
diff --git a/arkindex/training/api.py b/arkindex/training/api.py
index 66b6d00a377014677c08e54e7a3e8dcb5df39336..c7d7220ae96ece53f8fd0426cbd0f8d93f4396d6 100644
--- a/arkindex/training/api.py
+++ b/arkindex/training/api.py
@@ -417,8 +417,7 @@ class ModelsList(TrainingModelMixin, ListCreateAPIView):
"id": str(existing_model.id),
"name": "A model with this name already exists",
})
- else:
- raise PermissionDenied()
+ raise PermissionDenied()
return serializer.save()
@@ -753,7 +752,7 @@ class DatasetSetBase():
)
if self.request.method == "DELETE" and not Corpus.objects.admin(self.request.user).filter(pk=dataset.corpus_id).exists():
raise PermissionDenied(detail="You do not have admin access to this dataset.")
- elif self.request.method != "DELETE" and not Corpus.objects.writable(self.request.user).filter(pk=dataset.corpus_id).exists():
+ if self.request.method != "DELETE" and not Corpus.objects.writable(self.request.user).filter(pk=dataset.corpus_id).exists():
raise PermissionDenied(detail="You do not have contributor access to this dataset.")
if dataset.state != DatasetState.Open:
raise ValidationError(detail="You can only add or update sets from a dataset in an open state.")
diff --git a/arkindex/training/management/commands/migrate_workers.py b/arkindex/training/management/commands/migrate_workers.py
index 51e15165089905cc44b4063e851087dec1dfcbac..6e011fe5a60d43123819b71075eb2872f2fca0db 100644
--- a/arkindex/training/management/commands/migrate_workers.py
+++ b/arkindex/training/management/commands/migrate_workers.py
@@ -23,7 +23,7 @@ def ask(phrase):
choice = input(phrase + " [y/n]: ")
if choice.lower() == "y":
return True
- elif choice.lower() == "n":
+ if choice.lower() == "n":
return False
@@ -33,7 +33,7 @@ def choose(instances, name_field="name", title="Pick one item", allow_skip=False
nb = instances.count()
if nb == 0:
return
- elif nb == 1:
+ if nb == 1:
return instances.first()
# Build internal representation
diff --git a/arkindex/users/api.py b/arkindex/users/api.py
index 5c4b9c40df27caa4a3d55ae485281feecf084c26..467fd2e7283111cbab05450426c502e5c3ad0ee7 100644
--- a/arkindex/users/api.py
+++ b/arkindex/users/api.py
@@ -261,12 +261,11 @@ class PasswordReset(CreateAPIView):
status=status.HTTP_201_CREATED,
headers=headers,
)
- else:
- return Response(
- form.errors.get_json_data(),
- status=status.HTTP_400_BAD_REQUEST,
- headers=self.default_response_headers
- )
+ return Response(
+ form.errors.get_json_data(),
+ status=status.HTTP_400_BAD_REQUEST,
+ headers=self.default_response_headers
+ )
@extend_schema_view(post=extend_schema(operation_id="PasswordResetConfirm", tags=["users"]))
diff --git a/ruff.toml b/ruff.toml
index d14e149d84c88b14c3ea363299e958e3e6adffed..6def6e28921fcec79c3c996c8e4ad680dcaf05b8 100644
--- a/ruff.toml
+++ b/ruff.toml
@@ -7,7 +7,7 @@ quote-style = "double"
[lint]
select = [
# flake8-quotes
- "Q0",
+ "Q",
# pyflakes
"F",
# pycodestyle
@@ -17,8 +17,14 @@ select = [
"S113",
# isort
"I",
+ # flake8-debugger
+ "T10",
+ # escape-sequence-in-docstring
+ "D301",
+ # flake8-return
+ "RET",
]
-ignore = ["E501"]
+ignore = ["E501", "RET502", "RET503"]
[lint.isort]
default-section = "first-party"