fix: Fix error in field validation

Author: pierrepo

src/mdverse_scrapers/models/dataset.py

@@ -12,7 +12,8 @@
     model_validator,
 )
 
-from .enums import DatasetRepoProjectName
+from .date import DATETIME_FORMAT
+from .enums import DatasetSourceName
 from .simulation import SimulationMetadata
 
 DOI = Annotated[
@@ -31,7 +32,7 @@ class DatasetCoreMetadata(BaseModel):
     This model captures essential information about the source repository
     """
 
-    dataset_repository_name: DatasetRepoProjectName = Field(
+    dataset_repository_name: DatasetSourceName = Field(
         ...,
         description=(
             "Name of the source data repository. "
@@ -62,11 +63,11 @@ class DatasetMetadata(SimulationMetadata, DatasetCoreMetadata):
     # ------------------------------------------------------------------
     # Project metadata
     # ------------------------------------------------------------------
-    dataset_project_name: DatasetRepoProjectName | None = Field(
+    dataset_project_name: DatasetSourceName | None = Field(
         None,
         description=(
             "Name of the source data project. "
-            "Allowed values in the DatasetRepoProjectName enum. "
+            "Allowed values in the DatasetSourceName enum. "
             "Examples: ZENODO, FIGSHARE, NOMAD..."
         ),
     )
@@ -116,7 +117,7 @@ def date_last_fetched(self) -> str:
         str
             The current date and time in ISO 8601 format.
         """
-        return datetime.now().strftime("%Y-%m-%dT%H:%M:%S")
+        return datetime.now().strftime(DATETIME_FORMAT)
 
     # ------------------------------------------------------------------
     # Descriptive metadata
@@ -165,7 +166,8 @@ def date_last_fetched(self) -> str:
     # Validators
     # ------------------------------------------------------------------
     @field_validator("date_created", "date_last_updated", mode="before")
-    def format_dates(cls, value: datetime | str | None) -> str | None:  # noqa: N805
+    @classmethod
+    def format_dates(cls, value: datetime | str | None) -> str | None:
         """Convert datetime objects or strings to '%Y-%m-%dT%H:%M:%S' format.
 
         Parameters
@@ -183,8 +185,8 @@ def format_dates(cls, value: datetime | str | None) -> str | None:  # noqa: N805
         if value is None:
             return None
         if isinstance(value, datetime):
-            return value.strftime("%Y-%m-%dT%H:%M:%S")
-        return datetime.fromisoformat(value).strftime("%Y-%m-%dT%H:%M:%S")
+            return value.strftime(DATETIME_FORMAT)
+        return datetime.fromisoformat(value).strftime(DATETIME_FORMAT)
 
     @field_validator(
         "description",
@@ -194,7 +196,8 @@ def format_dates(cls, value: datetime | str | None) -> str | None:  # noqa: N805
         "author_names",
         mode="before",
     )
-    def empty_to_none(cls, value: list | str | None) -> list | str | None:  # noqa: N805
+    @classmethod
+    def empty_to_none(cls, value: list | str | None) -> list | str | None:
         """
         Normalize empty fields to None.
 

src/mdverse_scrapers/models/enums.py

@@ -10,8 +10,8 @@ class DataType(StrEnum):
     FILES = "files"
 
 
-class DatasetRepoProjectName(StrEnum):
-    """Molecular dynamaics data repositories and projects."""
+class DatasetSourceName(StrEnum):
+    """Molecular dynamics sources: data repositories and projects."""
 
     ZENODO = "zenodo"
     FIGSHARE = "figshare"

src/mdverse_scrapers/models/file.py

@@ -43,7 +43,8 @@ class FileMetadata(DatasetCoreMetadata):
     # Validators
     # ------------------------------------------------------------------
     @field_validator("file_size_in_bytes", mode="before")
-    def normalize_byte_string(cls, value: str | None) -> str | None:  # noqa: N805
+    @classmethod
+    def normalize_byte_string(cls, value: str | None) -> str | None:
         """
         Normalize the unit "Bytes" with "B" to make it acceptable for ByteSize.
 

src/mdverse_scrapers/models/simulation.py

@@ -82,8 +82,9 @@ class SimulationMetadata(BaseModel):
     # Validators
     # ------------------------------------------------------------------
     @field_validator("simulation_timesteps_in_fs", "simulation_times", mode="before")
+    @classmethod
     def validate_positive_simulation_values(
-        self,
+        cls,
         value: list[str | float] | None,
     ) -> list[str | float] | None:
         """Ensure simulation numeric parameters are strictly positive.
@@ -94,8 +95,8 @@ def validate_positive_simulation_values(
 
         Parameters
         ----------
-        self: SimulationMetadata
-            The Pydantic model instance being validated.
+        cls: SimulationMetadata
+            The Pydantic model class being validated.
         value : list[str | float] | None
             Raw input simulation parameter value.
 
@@ -134,8 +135,9 @@ def check_positive(value: str | float | int):
         return value
 
     @field_validator("simulation_temperatures_in_kelvin", mode="before")
+    @classmethod
     def normalize_temperatures(
-        self,
+        cls,
         temperatures: list[str] | None,
     ) -> list[float] | None:
         """
@@ -147,8 +149,8 @@ def normalize_temperatures(
 
         Parameters
         ----------
-        self: SimulationMetadata
-            The Pydantic model instance being validated.
+        cls: SimulationMetadata
+            The Pydantic model class being validated.
         temperatures : list[str] | None
             Raw temperature values.
 

tests/models/test_dataset.py

@@ -5,7 +5,8 @@
 import pytest
 
 from mdverse_scrapers.models.dataset import DatasetMetadata
-from mdverse_scrapers.models.enums import DatasetRepoProjectName
+from mdverse_scrapers.models.date import DATETIME_FORMAT
+from mdverse_scrapers.models.enums import DatasetSourceName
 
 
 # --------------------------------------
@@ -14,12 +15,12 @@
 def test_dataset_metadata_minimal_required_fields():
     """Test creating DatasetMetadata with only required fields."""
     metadata = DatasetMetadata(
-        dataset_repository_name=DatasetRepoProjectName.ZENODO,
+        dataset_repository_name=DatasetSourceName.ZENODO,
         dataset_id_in_repository="123",
         dataset_url_in_repository="https://zenodo.org/record/123",
         title="Test Dataset",
     )
-    assert metadata.dataset_repository_name == DatasetRepoProjectName.ZENODO
+    assert metadata.dataset_repository_name == DatasetSourceName.ZENODO
     assert metadata.dataset_id_in_repository == "123"
     assert metadata.dataset_url_in_repository == "https://zenodo.org/record/123"
     assert metadata.title == "Test Dataset"
@@ -43,7 +44,7 @@ def test_dataset_metadata_minimal_required_fields():
 def test_empty_to_none(field, value, expected):
     """Test that empty strings/lists are converted to None."""
     data = {
-        "dataset_repository_name": DatasetRepoProjectName.ZENODO,
+        "dataset_repository_name": DatasetSourceName.ZENODO,
         "dataset_id_in_repository": "123",
         "dataset_url_in_repository": "https://zenodo.org/record/123",
         "title": "Test Dataset",
@@ -60,14 +61,14 @@ def test_format_dates_with_datetime_objects():
     """Test that datetime objects are correctly converted to ISO string format."""
     now = datetime(2026, 1, 23, 12, 0, 0)
     metadata = DatasetMetadata(
-        dataset_repository_name=DatasetRepoProjectName.ZENODO,
+        dataset_repository_name=DatasetSourceName.ZENODO,
         dataset_id_in_repository="123",
         dataset_url_in_repository="https://zenodo.org/record/123",
         title="Test Dataset",
         date_created=now,
         date_last_updated=now,
     )
-    formatted = now.strftime("%Y-%m-%dT%H:%M:%S")
+    formatted = now.strftime(DATETIME_FORMAT)
     assert metadata.date_created == formatted
     assert metadata.date_last_updated == formatted
 
@@ -76,7 +77,7 @@ def test_format_dates_with_iso_strings():
     """Test that ISO string dates are normalized to '%Y-%m-%dT%H:%M:%S' format."""
     expected_date = "2026-01-23T00:00:00"
     metadata = DatasetMetadata(
-        dataset_repository_name=DatasetRepoProjectName.ZENODO,
+        dataset_repository_name=DatasetSourceName.ZENODO,
         dataset_id_in_repository="123",
         dataset_url_in_repository="https://zenodo.org/record/123",
         title="Test Dataset",
@@ -91,15 +92,15 @@ def test_format_dates_with_iso_strings():
 def test_fill_project_fields():
     """Test that project fields are populated from repository fields when missing."""
     metadata = DatasetMetadata(
-        dataset_repository_name=DatasetRepoProjectName.ZENODO,
+        dataset_repository_name=DatasetSourceName.ZENODO,
         dataset_id_in_repository="repo_123",
         dataset_url_in_repository="https://zenodo.org/record/repo_123",
         dataset_project_name=None,
         dataset_id_in_project=None,
         dataset_url_in_project=None,
         title="Test Dataset",
     )
-    assert metadata.dataset_project_name == DatasetRepoProjectName.ZENODO
+    assert metadata.dataset_project_name == DatasetSourceName.ZENODO
     assert metadata.dataset_id_in_project == "repo_123"
     assert metadata.dataset_url_in_project == "https://zenodo.org/record/repo_123"
 
@@ -108,7 +109,7 @@ def test_fill_project_fields_from_repository_invalid_mapping():
     """Test that ValueError is raised when repository cannot map to a project."""
     with pytest.raises(AttributeError, match="type object"):
         _ = DatasetMetadata(
-            dataset_repository_name=DatasetRepoProjectName.REPO,
+            dataset_repository_name=DatasetSourceName.DUMMY,
             dataset_id_in_repository="123",
             dataset_url_in_repository="https://example.com/123",
             title="Test Dataset",
@@ -119,7 +120,7 @@ def test_date_last_fetched_is_recent():
     """Test that date_last_fetched is a recent datetime."""
     time_1 = datetime.now()
     metadata = DatasetMetadata(
-        dataset_repository_name=DatasetRepoProjectName.ZENODO,
+        dataset_repository_name=DatasetSourceName.ZENODO,
         dataset_id_in_repository="123",
         dataset_url_in_repository="https://zenodo.org/record/123",
         title="Test Dataset",
@@ -136,7 +137,7 @@ def test_date_last_fetched_is_recent():
 def test_dataset_metadata_full_scenario():
     """Test a realistic scenario with mixed missing fields and validators."""
     metadata = DatasetMetadata(
-        dataset_repository_name=DatasetRepoProjectName.FIGSHARE,
+        dataset_repository_name=DatasetSourceName.FIGSHARE,
         dataset_id_in_repository="fig_456",
         dataset_url_in_repository="https://figshare.com/articles/fig_456",
         dataset_project_name=None,
@@ -156,7 +157,7 @@ def test_dataset_metadata_full_scenario():
     assert metadata.external_links is None
     assert metadata.license is None
     # Check project fields filled
-    assert metadata.dataset_project_name == DatasetRepoProjectName.FIGSHARE
+    assert metadata.dataset_project_name == DatasetSourceName.FIGSHARE
     assert metadata.dataset_id_in_project == "fig_456"
     assert metadata.dataset_url_in_project == "https://figshare.com/articles/fig_456"
     # Check date_last_fetched is filled

tests/models/test_file.py

@@ -3,14 +3,14 @@
 import pytest
 from pydantic import ByteSize
 
-from mdverse_scrapers.models.enums import DatasetRepoProjectName
+from mdverse_scrapers.models.enums import DatasetSourceName
 from mdverse_scrapers.models.file import FileMetadata
 
 
 def test_file_metadata_basic_creation():
     """Test creating a FileMetadata instance with minimal required fields."""
     file = FileMetadata(
-        dataset_repository_name=DatasetRepoProjectName.NOMAD,
+        dataset_repository_name=DatasetSourceName.NOMAD,
         dataset_id_in_repository="abc123",
         dataset_url_in_repository="https://example.com",
         file_url_in_repository="https://example.com/file.xtc",
@@ -41,7 +41,7 @@ def test_file_size_normalization(
 ) -> None:
     """Test file size normalization."""
     file = FileMetadata(
-        dataset_repository_name=DatasetRepoProjectName.ZENODO,
+        dataset_repository_name=DatasetSourceName.ZENODO,
         dataset_id_in_repository="abc123",
         dataset_url_in_repository="https://example.com",
         file_url_in_repository="https://example.com/file.xtc",
@@ -67,12 +67,13 @@ def test_file_size_normalization(
         ("complex.name.with.many.dots.pdb", "pdb"),
         ("complex/path/to/file.pdb", "pdb"),
         ("very.complex/path/to/file.pdb", "pdb"),
+        ("long path/with/some spaces/to/this_file.txt", "txt"),
     ],
 )
 def test_file_type_computed_correctly(file_name: str, expected_file_type: str) -> None:
     """Test that file_type is computed correctly from the file_name."""
     file = FileMetadata(
-        dataset_repository_name=DatasetRepoProjectName.NOMAD,
+        dataset_repository_name=DatasetSourceName.NOMAD,
         dataset_id_in_repository="abc123",
         dataset_url_in_repository="https://example.com",
         file_url_in_repository="https://example.com/file",