Bump ruff linter and add formatter

.pre-commit-config.yaml

 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.0.278
+    rev: v0.1.6
     hooks:
+      # Run the linter.
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]
         exclude: "^worker-{{cookiecutter.slug}}/"
-  - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 23.11.0
-    hooks:
-    - id: black
+      # Run the formatter.
+      - id: ruff-format
+        exclude: "^worker-{{cookiecutter.slug}}/"
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.4.0
     hooks:

arkindex_worker/worker/classification.py

@@ -204,8 +204,8 @@ class ClassificationMixin(object):
 
         for index, classification in enumerate(classifications):
             ml_class_id = classification.get("ml_class_id")
-            assert ml_class_id and isinstance(
-                ml_class_id, str
+            assert (
+                ml_class_id and isinstance(ml_class_id, str)
             ), f"Classification at index {index} in classifications: ml_class_id shouldn't be null and should be of type str"
 
             # Make sure it's a valid UUID

arkindex_worker/worker/element.py

@@ -195,18 +195,18 @@ class ElementMixin(object):
             ), f"Element at index {index} in elements: Should be of type dict"
 
             name = element.get("name")
-            assert name and isinstance(
-                name, str
+            assert (
+                name and isinstance(name, str)
             ), f"Element at index {index} in elements: name shouldn't be null and should be of type str"
 
             type = element.get("type")
-            assert type and isinstance(
-                type, str
+            assert (
+                type and isinstance(type, str)
             ), f"Element at index {index} in elements: type shouldn't be null and should be of type str"
 
             polygon = element.get("polygon")
-            assert polygon and isinstance(
-                polygon, list
+            assert (
+                polygon and isinstance(polygon, list)
             ), f"Element at index {index} in elements: polygon shouldn't be null and should be of type list"
             assert (
                 len(polygon) >= 3
@@ -219,8 +219,9 @@ class ElementMixin(object):
             ), f"Element at index {index} in elements: polygon points should be lists of two numbers"
 
             confidence = element.get("confidence")
-            assert confidence is None or (
-                isinstance(confidence, float) and 0 <= confidence <= 1
+            assert (
+                confidence is None
+                or (isinstance(confidence, float) and 0 <= confidence <= 1)
             ), f"Element at index {index} in elements: confidence should be None or a float in [0..1] range"
 
         if self.is_read_only:
@@ -485,11 +486,14 @@ class ElementMixin(object):
 
         if self.use_cache:
             # Checking that we only received query_params handled by the cache
-            assert set(query_params.keys()) <= {
-                "type",
-                "worker_version",
-                "worker_run",
-            }, "When using the local cache, you can only filter by 'type' and/or 'worker_version' and/or 'worker_run'"
+            assert (
+                set(query_params.keys())
+                <= {
+                    "type",
+                    "worker_version",
+                    "worker_run",
+                }
+            ), "When using the local cache, you can only filter by 'type' and/or 'worker_version' and/or 'worker_run'"
 
             query = CachedElement.select().where(CachedElement.parent_id == element.id)
             if type:
@@ -644,11 +648,14 @@ class ElementMixin(object):
 
         if self.use_cache:
             # Checking that we only received query_params handled by the cache
-            assert set(query_params.keys()) <= {
-                "type",
-                "worker_version",
-                "worker_run",
-            }, "When using the local cache, you can only filter by 'type' and/or 'worker_version' and/or 'worker_run'"
+            assert (
+                set(query_params.keys())
+                <= {
+                    "type",
+                    "worker_version",
+                    "worker_run",
+                }
+            ), "When using the local cache, you can only filter by 'type' and/or 'worker_version' and/or 'worker_run'"
 
             parent_ids = CachedElement.select(CachedElement.parent_id).where(
                 CachedElement.id == element.id

arkindex_worker/worker/entity.py

@@ -250,13 +250,13 @@ class EntityMixin(object):
             ), f"Entity at index {index} in entities: Should be of type dict"
 
             name = entity.get("name")
-            assert name and isinstance(
-                name, str
+            assert (
+                name and isinstance(name, str)
             ), f"Entity at index {index} in entities: name shouldn't be null and should be of type str"
 
             type_id = entity.get("type_id")
-            assert type_id and isinstance(
-                type_id, str
+            assert (
+                type_id and isinstance(type_id, str)
             ), f"Entity at index {index} in entities: type_id shouldn't be null and should be of type str"
 
             offset = entity.get("offset")
@@ -270,8 +270,9 @@ class EntityMixin(object):
             ), f"Entity at index {index} in entities: length shouldn't be null and should be a strictly positive integer"
 
             confidence = entity.get("confidence")
-            assert confidence is None or (
-                isinstance(confidence, float) and 0 <= confidence <= 1
+            assert (
+                confidence is None
+                or (isinstance(confidence, float) and 0 <= confidence <= 1)
             ), f"Entity at index {index} in entities: confidence should be None or a float in [0..1] range"
 
         assert len(entities) == len(

arkindex_worker/worker/training.py

@@ -235,9 +235,7 @@ class TrainingMixin(object):
         ), "The model is already marked as available."
 
         s3_put_url = self.model_version.get("s3_put_url")
-        assert (
-            s3_put_url
-        ), "S3 PUT URL is not set, please ensure you have the right to validate a model version."
+        assert s3_put_url, "S3 PUT URL is not set, please ensure you have the right to validate a model version."
 
         logger.info("Uploading to s3...")
         # Upload the archive on s3
@@ -263,9 +261,7 @@ class TrainingMixin(object):
         :param size: The size of the uploaded archive
         :param archive_hash: MD5 hash of the uploaded archive
         """
-        assert (
-            self.model_version
-        ), "You must create the model version and upload its archive before validating it."
+        assert self.model_version, "You must create the model version and upload its archive before validating it."
         try:
             self.model_version = self.request(
                 "ValidateModelVersion",

arkindex_worker/worker/transcription.py

@@ -140,13 +140,13 @@ class TranscriptionMixin(object):
 
         for index, transcription in enumerate(transcriptions_payload):
             element_id = transcription.get("element_id")
-            assert element_id and isinstance(
-                element_id, str
+            assert (
+                element_id and isinstance(element_id, str)
             ), f"Transcription at index {index} in transcriptions: element_id shouldn't be null and should be of type str"
 
             text = transcription.get("text")
-            assert text and isinstance(
-                text, str
+            assert (
+                text and isinstance(text, str)
             ), f"Transcription at index {index} in transcriptions: text shouldn't be null and should be of type str"
 
             confidence = transcription.get("confidence")
@@ -159,8 +159,8 @@ class TranscriptionMixin(object):
             orientation = transcription.get(
                 "orientation", TextOrientation.HorizontalLeftToRight
             )
-            assert orientation and isinstance(
-                orientation, TextOrientation
+            assert (
+                orientation and isinstance(orientation, TextOrientation)
             ), f"Transcription at index {index} in transcriptions: orientation shouldn't be null and should be of type TextOrientation"
             if orientation:
                 transcription["orientation"] = orientation.value
@@ -242,8 +242,8 @@ class TranscriptionMixin(object):
 
         for index, transcription in enumerate(transcriptions_payload):
             text = transcription.get("text")
-            assert text and isinstance(
-                text, str
+            assert (
+                text and isinstance(text, str)
             ), f"Transcription at index {index} in transcriptions: text shouldn't be null and should be of type str"
 
             confidence = transcription.get("confidence")
@@ -256,15 +256,15 @@ class TranscriptionMixin(object):
             orientation = transcription.get(
                 "orientation", TextOrientation.HorizontalLeftToRight
             )
-            assert orientation and isinstance(
-                orientation, TextOrientation
+            assert (
+                orientation and isinstance(orientation, TextOrientation)
             ), f"Transcription at index {index} in transcriptions: orientation shouldn't be null and should be of type TextOrientation"
             if orientation:
                 transcription["orientation"] = orientation.value
 
             polygon = transcription.get("polygon")
-            assert polygon and isinstance(
-                polygon, list
+            assert (
+                polygon and isinstance(polygon, list)
             ), f"Transcription at index {index} in transcriptions: polygon shouldn't be null and should be of type list"
             assert (
                 len(polygon) >= 3
@@ -277,8 +277,12 @@ class TranscriptionMixin(object):
             ), f"Transcription at index {index} in transcriptions: polygon points should be lists of two numbers"
 
             element_confidence = transcription.get("element_confidence")
-            assert element_confidence is None or (
-                isinstance(element_confidence, float) and 0 <= element_confidence <= 1
+            assert (
+                element_confidence is None
+                or (
+                    isinstance(element_confidence, float)
+                    and 0 <= element_confidence <= 1
+                )
             ), f"Transcription at index {index} in transcriptions: element_confidence should be either null or a float in [0..1] range"
 
         if self.is_read_only:

pyproject.toml

 [tool.ruff]
 exclude = [".git", "__pycache__"]
 ignore = ["E501"]
-select = ["E", "F", "T1", "W", "I"]
+select = [
+    # pycodestyle
+    "E",
+    "W",
+    # Pyflakes
+    "F",
+    # Flake8 Debugger
+    "T1",
+    # Isort
+    "I",
+]
 
 [tool.ruff.isort]
 known-first-party = ["arkindex", "arkindex_common", "arkindex_worker"]