Add defaults and check_illegal_characters field

nomenclature/codelist.py

@@ -335,22 +335,24 @@ def read_excel(cls, name, source, sheet_name, col, attrs=None):
 
         return cls(name=name, mapping=mapp)
 
-    def check_illegal_characters(
-        self, config: NomenclatureConfig = None
-    ) -> Dict[str, Code]:
+    def check_illegal_characters(self, config: NomenclatureConfig) -> Dict[str, Code]:
         """Check that no illegal characters are left in codes after tag replacement"""
-        forbidden = ["{", "}"]
-        if config and config.illegal_characters:
-            forbidden += config.illegal_characters
+        illegal = (
+            ["{", "}"] + config.illegal_characters
+            if config.check_illegal_characters
+            else ["{", "}"]
+        )
 
         def _check_string(value):
             if isinstance(value, str):
-                if any(char in value for char in forbidden):
+                if any(char in value for char in illegal):
                     raise ValueError(
                         f"Unexpected character in {self.name}: '{code.name}'."
                         " Check for illegal characters and/or if tags were spelled correctly."
                     )
             elif isinstance(value, dict):
+                for k in value.keys():
+                    _check_string(k)
                 for v in value.values():
                     _check_string(v)
             elif isinstance(value, list):
@@ -360,7 +362,7 @@ def _check_string(value):
         for code in self.mapping.values():
             if not code.repository:
                 for attr in code.model_fields:
-                    if attr not in ["file", "repository"]:
+                    if attr != "file":
                         value = getattr(code, attr)
                         _check_string(value)
 

nomenclature/config.py

@@ -159,13 +159,14 @@ class NomenclatureConfig(BaseModel):
     repositories: dict[str, Repository] = Field(default_factory=dict)
     definitions: DataStructureConfig = Field(default_factory=DataStructureConfig)
     mappings: RegionMappingConfig = Field(default_factory=RegionMappingConfig)
-    illegal_characters: None | list[str] = None
+    check_illegal_characters: bool = True
+    illegal_characters: list[str] = ["'", ":", ";"]
 
     model_config = ConfigDict(use_enum_values=True)
 
     @field_validator("illegal_characters", mode="before")
     @classmethod
-    def check_illegal_characters(cls, v: str | list[str]) -> list[str]:
+    def check_illegal_chars(cls, v: str | list[str]) -> list[str]:
         return v if isinstance(v, list) else [v]
 
     @model_validator(mode="after")

tests/data/codelist/illegal_chars/char_in_external_repo/nomenclature.yaml

@@ -8,4 +8,5 @@ definitions:
   variable:
     repository:
       - common-definitions
-illegal_characters: ['"' , ";"]  # these are known to be present in common-definitions variables
+check_illegal_characters: true
+illegal_characters: ['"' , ";"]  # these are known to be present in common-definitions variables

tests/data/config/general-config-only-country/nomenclature.yaml

@@ -3,3 +3,4 @@ dimensions:
 definitions:
   region:
     country: true
+illegal_characters: [";", ":"]

tests/test_codelist.py

@@ -236,7 +236,7 @@ def test_stray_tag_fails(subfolder, match):
         code_list = VariableCodeList.from_directory(
             "variable", MODULE_TEST_DATA_DIR / "stray_tag" / subfolder
         )
-        code_list.check_illegal_characters()
+        code_list.check_illegal_characters(NomenclatureConfig(dimensions=["variable"]))
 
 
 def test_illegal_char_fails():