style: update ruff

.pre-commit-config.yaml

@@ -10,7 +10,7 @@ repos:
       - id: detect-aws-credentials
         args: [ --allow-missing-credentials ]
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.5.0  # ruff version
+    rev: v0.8.4  # ruff version
     hooks:
       - id: ruff-format
       - id: ruff

pyproject.toml

@@ -45,7 +45,7 @@ dynamic = ["version"]
 
 [project.optional-dependencies]
 tests = ["pytest", "pytest-cov", "mock", "pytest-asyncio", "deepdiff"]
-dev = ["pre-commit>=3.7.1", "ruff==0.5.0"]
+dev = ["pre-commit>=3.7.1", "ruff==0.8.4"]
 notebooks = ["ipykernel", "jupyterlab"]
 docs = [
     "sphinx==6.1.3",
@@ -116,10 +116,14 @@ select = [
     "RSE",  # https://docs.astral.sh/ruff/rules/#flake8-raise-rse
     "RET",  # https://docs.astral.sh/ruff/rules/#flake8-return-ret
     "SLF",  # https://docs.astral.sh/ruff/rules/#flake8-self-slf
+    "SLOT",  # https://docs.astral.sh/ruff/rules/#flake8-slots-slot
     "SIM",  # https://docs.astral.sh/ruff/rules/#flake8-simplify-sim
     "ARG",  # https://docs.astral.sh/ruff/rules/#flake8-unused-arguments-arg
     "PTH",  # https://docs.astral.sh/ruff/rules/#flake8-use-pathlib-pth
     "PGH",  # https://docs.astral.sh/ruff/rules/#pygrep-hooks-pgh
+    "PLC",  # https://docs.astral.sh/ruff/rules/#convention-c
+    "PLE",  # https://docs.astral.sh/ruff/rules/#error-e_1
+    "TRY",  # https://docs.astral.sh/ruff/rules/#tryceratops-try
     "PERF",  # https://docs.astral.sh/ruff/rules/#perflint-perf
     "FURB",  # https://docs.astral.sh/ruff/rules/#refurb-furb
     "RUF",  # https://docs.astral.sh/ruff/rules/#ruff-specific-rules-ruf
@@ -138,13 +142,14 @@ fixable = [
     "PT",
     "RSE",
     "SIM",
+    "PLC",
+    "PLE",
+    "TRY",
     "PERF",
     "FURB",
     "RUF"
 ]
 # ANN003 - missing-type-kwargs
-# ANN101 - missing-type-self
-# ANN102 - missing-type-cls
 # D203 - one-blank-line-before-class
 # D205 - blank-line-after-summary
 # D206 - indent-with-spaces*
@@ -158,19 +163,22 @@ fixable = [
 # E501 - line-too-long*
 # W191 - tab-indentation*
 # S321 - suspicious-ftp-lib-usage
+# PLC0206 - dict-index-missing-items
 # *ignored for compatibility with formatter
 ignore = [
-    "ANN003", "ANN101", "ANN102",
+    "ANN003",
     "D203", "D205", "D206", "D213", "D300", "D400", "D415",
     "E111", "E114", "E117", "E501",
     "W191",
     "S321",
+    "PLC0206",
 ]
 
 [tool.ruff.lint.per-file-ignores]
 # ANN001 - missing-type-function-argument
 # ANN2 - missing-return-type
-# ANN102 - missing-type-cls
+# D100 - undocumented-public-module
+# D102 - undocumented-public-class
 # S101 - assert
 # B011 - assert-false
 # D104 - undocumented-public-package
@@ -179,5 +187,23 @@ ignore = [
 # ARG001 - unused-function-argument
 # SLF001 - private-member-acces
 # N815 - mixed-case-variable-in-class-scope
-"tests/*" = ["ANN001", "ANN2", "ANN102", "S101", "B011", "D100", "D104", "INP001", "SLF001", "ARG001"]
+"tests/*" = [
+    "ANN001",
+    "ANN2",
+    "D100",
+    "D102",
+    "S101",
+    "B011",
+    "D100",
+    "D104",
+    "INP001",
+    "SLF001",
+    "ARG001"
+]
 "src/metakb/schemas/*" = ["ANN102", "N815"]
+
+[tool.ruff.lint.flake8-annotations]
+mypy-init-return = true
+
+[tool.ruff.format]
+docstring-code-format = true

src/metakb/cli.py

@@ -171,13 +171,13 @@ def update_normalizers(
                 f"prohibited. Unset the environment variable "
                 f"{NORMALIZER_AWS_ENV_VARS[name]} to proceed."
             )
-            _logger.error(msg)
+            _logger.exception(msg)
             click.echo(msg)
             success = False
             continue
-        except (Exception, SystemExit) as e:
-            _logger.error(
-                "Encountered error while updating %s database: %s", name.value, e
+        except (Exception, SystemExit):
+            _logger.exception(
+                "Encountered error while updating %s database", name.value
             )
             click.echo(f"Failed to update {name.value} normalizer.")
             success = False

src/metakb/database.py

@@ -25,11 +25,11 @@ def _get_secret() -> str:
 
     try:
         get_secret_value_response = client.get_secret_value(SecretId=secret_name)
-    except ClientError as e:
+    except ClientError:
         # For a list of exceptions thrown, see
         # https://docs.aws.amazon.com/secretsmanager/latest/apireference/API_GetSecretValue.html
-        logger.error(e)
-        raise e
+        logger.exception("Boto client error while acquiring secrets")
+        raise
     else:
         return get_secret_value_response["SecretString"]
 

src/metakb/harvesters/base.py

@@ -75,7 +75,7 @@ def save_harvested_data_to_file(
         try:
             with (harvested_filepath).open("w+") as f:
                 json.dump(harvested_data.model_dump(), f, indent=2)
-        except Exception as e:
-            logger.error("Error creating %s harvester JSON: %s", src_name, e)
+        except Exception:
+            logger.exception("Error creating %s harvester JSON", src_name)
             return False
         return True

src/metakb/load_data.py

@@ -489,7 +489,7 @@ def add_transformed_data(driver: Driver, data: dict) -> None:
         for method in data.get("methods", []):
             session.execute_write(_add_method, method, ids_in_stmts)
 
-        for obj_type in {"genes", "conditions"}:
+        for obj_type in ("genes", "conditions"):
             for obj in data.get(obj_type, []):
                 session.execute_write(_add_gene_or_disease, obj, ids_in_stmts)
 

src/metakb/normalizers.py

@@ -33,12 +33,12 @@
 from variation.query import QueryHandler as VariationQueryHandler
 
 __all__ = [
-    "ViccNormalizers",
+    "NORMALIZER_AWS_ENV_VARS",
+    "IllegalUpdateError",
     "NormalizerName",
+    "ViccNormalizers",
     "check_normalizers",
-    "IllegalUpdateError",
     "update_normalizer",
-    "NORMALIZER_AWS_ENV_VARS",
 ]
 
 _logger = logging.getLogger(__name__)
@@ -90,7 +90,9 @@ def __init__(self, db_url: str | None = None) -> None:
         Note that gene concept lookups within the Variation Normalizer are resolved
         using the Gene Normalizer instance, rather than creating a second sub-instance.
 
-        >>> id(norm.gene_query_handler) == id(norm.variation_normalizer.gnomad_vcf_to_protein_handler.gene_normalizer)
+        >>> id(norm.gene_query_handler) == id(
+        ...     norm.variation_normalizer.gnomad_vcf_to_protein_handler.gene_normalizer
+        ... )
         True
 
         :param db_url: optional definition of shared normalizer database. Because the
@@ -127,14 +129,16 @@ async def normalize_variation(
                 )
                 if variation_norm_resp and variation_norm_resp.variation:
                     return variation_norm_resp.variation
-            except TokenRetrievalError as e:
-                _logger.error(e)
-                raise e
-            except Exception as e:
-                _logger.error(
-                    "Variation Normalizer raised an exception using query %s: %s",
+            except TokenRetrievalError:
+                _logger.exception(
+                    "Variation Normalizer encountered boto token retrieval error for query %s",
+                    query,
+                )
+                raise
+            except Exception:
+                _logger.exception(
+                    "Variation Normalizer raised an exception using query %s",
                     query,
-                    e,
                 )
         return None
 
@@ -173,14 +177,16 @@ def normalize_gene(
 
             try:
                 gene_norm_resp = self.gene_query_handler.normalize(query_str)
-            except TokenRetrievalError as e:
-                _logger.error(e)
-                raise e
-            except Exception as e:
-                _logger.error(
-                    "Gene Normalizer raised an exception using query %s: %s",
+            except TokenRetrievalError:
+                _logger.exception(
+                    "Gene Normalizer encountered boto token retrieval error fetching query %s",
+                    query_str,
+                )
+                raise
+            except Exception:
+                _logger.exception(
+                    "Gene Normalizer raised an exception fetching query %s",
                     query_str,
-                    e,
                 )
             else:
                 if gene_norm_resp.match_type > highest_match:
@@ -223,14 +229,16 @@ def normalize_disease(
 
             try:
                 disease_norm_resp = self.disease_query_handler.normalize(query)
-            except TokenRetrievalError as e:
-                _logger.error(e)
-                raise e
-            except Exception as e:
-                _logger.error(
-                    "Disease Normalizer raised an exception using query %s: %s",
+            except TokenRetrievalError:
+                _logger.exception(
+                    "Disease Normalizer encountered boto retrieval error while fetching term %s",
+                    query,
+                )
+                raise
+            except Exception:
+                _logger.exception(
+                    "Disease Normalizer raised an exception using query %s",
                     query,
-                    e,
                 )
             else:
                 if disease_norm_resp.match_type > highest_match:
@@ -273,14 +281,16 @@ def normalize_therapy(
 
             try:
                 therapy_norm_resp = self.therapy_query_handler.normalize(query)
-            except TokenRetrievalError as e:
-                _logger.error(e)
-                raise e
-            except Exception as e:
-                _logger.error(
-                    "Therapy Normalizer raised an exception using query %s: %s",
+            except TokenRetrievalError:
+                _logger.exception(
+                    "Failed to retrieve from boto while fetching therapy query %s",
+                    query,
+                )
+                raise
+            except Exception:
+                _logger.exception(
+                    "Therapy Normalizer raised an exception using query %s",
                     query,
-                    e,
                 )
             else:
                 if therapy_norm_resp.match_type > highest_match:
@@ -424,9 +434,9 @@ def check_normalizers(
                     "Tables for %s normalizer appear to be unpopulated.", name.value
                 )
                 success = False
-        except Exception as e:
-            _logger.error(
-                "Encountered exception while checking %s normalizer: %s", name.value, e
+        except Exception:
+            _logger.exception(
+                "Encountered exception while checking %s normalizer", name.value
             )
             success = False
     return success

src/metakb/query.py

@@ -116,7 +116,7 @@ def __init__(
         >>> from metakb.normalizers import ViccNormalizers
         >>> qh = QueryHandler(
         ...     get_driver("bolt://localhost:7687", ("neo4j", "password")),
-        ...     ViccNormalizers("http://localhost:8000")
+        ...     ViccNormalizers("http://localhost:8000"),
         ... )
 
         ``default_page_limit`` sets the default max number of statements to include in
@@ -129,10 +129,7 @@ def __init__(
 
         This value is overruled by an explicit ``limit`` parameter:
 
-        >>> response = await limited_qh.batch_search_statements(
-        ...     ["BRAF V600E"],
-        ...     limit=2
-        ... )
+        >>> response = await limited_qh.batch_search_statements(["BRAF V600E"], limit=2)
         >>> print(len(response.statement_ids))
         2
 
@@ -491,8 +488,8 @@ def _get_nested_stmts(self, statement_nodes: list[Node]) -> list[dict]:
             if s_id not in added_stmts:
                 try:
                     nested_stmt = self._get_nested_stmt(s)
-                except ValidationError as e:
-                    logger.error("%s: %s", s_id, e)
+                except ValidationError:
+                    logger.exception("Validation error while constructing %s", s_id)
                 else:
                     if nested_stmt:
                         nested_stmts.append(nested_stmt)