Merge pull request #161 from BIH-CEI/154-rename-compliance-literals

renamed compliance from soft and hard to lenient and strict

notebooks/erdri_cds_definition_in_code.ipynb

@@ -802,7 +802,7 @@
     "    genetic_diagnosis_column= \"6.2. Genetic diagnosis\",\n",
     "    undiagnosed_case_column= None,\n",
     "    \n",
-    "    compliance='soft'  # 'soft' or 'hard'\n",
+    "    compliance='lenient'  # 'lenient' or 'strict'\n",
     ")"
    ],
    "metadata": {

src/phenopacket_mapper/data_standards/code.py

@@ -25,7 +25,7 @@ class Coding:
     def parse_coding(
             coding_str: str,
             resources: List[CodeSystem],
-            compliance: Literal['soft', 'hard'] = 'soft'
+            compliance: Literal['lenient', 'strict'] = 'lenient'
     ) -> 'Coding':
         """Parsed a string representing a coding to a Coding object
 

src/phenopacket_mapper/data_standards/data_model.py

@@ -198,7 +198,7 @@ def get_field_ids(self) -> List[str]:
     def load_data(
             self,
             path: Union[str, Path],
-            compliance: Literal['soft', 'hard'] = 'soft',
+            compliance: Literal['lenient', 'strict'] = 'lenient',
             **kwargs
     ) -> 'DataSet':
         """Loads data from a file using a DataModel definition
@@ -285,16 +285,16 @@ def load_data_using_data_model(
             path: Union[str, Path],
             data_model: 'DataModel',
             column_names: Dict[str, str],
-            compliance: Literal['soft', 'hard'] = 'soft',
+            compliance: Literal['lenient', 'strict'] = 'lenient',
     ) -> 'DataSet':
         """Loads data from a file using a DataModel definition
 
         :param path: Path to  formatted csv or excel file
         :param data_model: DataModel to use for reading the file
         :param column_names: A dictionary mapping from the id of each field of the `DataField` to the name of a
                             column in the file
-        :param compliance: Compliance level to enforce when reading the file. If 'soft', the file can have extra fields
-                            that are not in the DataModel. If 'hard', the file must have all fields in the DataModel.
+        :param compliance: Compliance level to enforce when reading the file. If 'lenient', the file can have extra fields
+                            that are not in the DataModel. If 'strict', the file must have all fields in the DataModel.
         :return: List of DataModelInstances
         """
         from phenopacket_mapper.pipeline import load_data_using_data_model
@@ -315,14 +315,14 @@ class DataModelInstance:
     :ivar row_no: The id of the instance, i.e. the row number
     :ivar data_model: The `DataModel` object that defines the data model for this instance
     :ivar values: A list of `DataFieldValue` objects, each adhering to the `DataField` definition in the `DataModel`
-    :ivar compliance: Compliance level to enforce when validating the instance. If 'soft', the instance can have extra
-                        fields that are not in the DataModel. If 'hard', the instance must have all fields in the
+    :ivar compliance: Compliance level to enforce when validating the instance. If 'lenient', the instance can have extra
+                        fields that are not in the DataModel. If 'strict', the instance must have all fields in the
                         DataModel.
     """
     row_no: Union[int, str]
     data_model: DataModel
     values: List[DataFieldValue]
-    compliance: Literal['soft', 'hard'] = 'soft'
+    compliance: Literal['lenient', 'strict'] = 'lenient'
 
     def __post_init__(self):
         self.validate()
@@ -338,9 +338,9 @@ def validate(self) -> bool:
         error_msg = f"Instance values do not comply with their respective fields' valuesets. (row {self.row_no})"
         for v in self.values:
             if not v.validate():
-                if self.compliance == 'hard':
+                if self.compliance == 'strict':
                     raise ValueError(error_msg)
-                elif self.compliance == 'soft':
+                elif self.compliance == 'lenient':
                     warnings.warn(error_msg)
                     return False
                 else:
@@ -352,9 +352,9 @@ def validate(self) -> bool:
         if len(missing_fields := (is_required - fields_present)) > 0:
             error_msg = (f"Required fields are missing in the instance. (row {self.row_no}) "
                          f"\n(missing_fields={', '.join(missing_fields)})")
-            if self.compliance == 'hard':
+            if self.compliance == 'strict':
                 raise ValueError(error_msg)
-            elif self.compliance == 'soft':
+            elif self.compliance == 'lenient':
                 warnings.warn(error_msg)
                 return False
             else:

src/phenopacket_mapper/data_standards/date.py

@@ -212,7 +212,7 @@ def from_iso_8601(iso_8601: str) -> Union['Date', None]:
     def parse_date(
             date_str: str,
             default_first: Literal["day", "month"] = "day",
-            compliance: Literal['soft', 'hard'] = 'soft',
+            compliance: Literal['lenient', 'strict'] = 'lenient',
     ) -> 'Date':
         """Parse a date string into a Date object
 

src/phenopacket_mapper/data_standards/value_set.py

@@ -66,7 +66,7 @@ def parse_value_set(
             value_set_name: str = "",
             value_set_description: str = "",
             resources: List[CodeSystem] = None,
-            compliance: Literal['hard', 'soft'] = 'soft',
+            compliance: Literal['strict', 'lenient'] = 'lenient',
     ) -> 'ValueSet':
         """Parses a value set from a string representation
 

src/phenopacket_mapper/pipeline/input.py

@@ -142,7 +142,7 @@ def load_data_using_data_model(
         path: Union[str, Path],
         data_model: DataModel,
         column_names: Dict[str, str],
-        compliance: Literal['soft', 'hard'] = 'soft',
+        compliance: Literal['lenient', 'strict'] = 'lenient',
 ) -> DataSet:
     """Loads data from a file using a DataModel definition
 
@@ -160,8 +160,8 @@ def load_data_using_data_model(
     :param data_model: DataModel to use for reading the file
     :param column_names: A dictionary mapping from the id of each field of the `DataField` to the name of a
                         column in the file
-    :param compliance: Compliance level to enforce when reading the file. If 'soft', the file can have extra fields
-                        that are not in the DataModel. If 'hard', the file must have all fields in the DataModel.
+    :param compliance: Compliance level to enforce when reading the file. If 'lenient', the file can have extra fields
+                        that are not in the DataModel. If 'strict', the file must have all fields in the DataModel.
     :return: List of DataModelInstances
     """
     if isinstance(path, Path):

src/phenopacket_mapper/utils/parsing/parse_coding.py

@@ -9,7 +9,7 @@
 def parse_coding(
         coding_str: str,
         resources: List[CodeSystem],
-        compliance: Literal['soft', 'hard'] = 'soft'
+        compliance: Literal['lenient', 'strict'] = 'lenient'
 ) -> Coding:
     """Parsed a string representing a coding to a Coding object
 
@@ -56,7 +56,7 @@ def parse_coding(
         if code_system:
             return Coding(system=code_system, code=code)
         else:
-            if compliance == 'hard':
+            if compliance == 'strict':
                 raise ValueError(f"Code system with namespace prefix '{namespace_prefix}' not found in resources.")
             else:
                 print(f"Warning: Code system with namespace prefix '{namespace_prefix}' not found in resources.")

src/phenopacket_mapper/utils/parsing/parse_data_type.py

@@ -16,7 +16,7 @@
 def parse_data_type(
         type_str: str,
         resources: List[CodeSystem],
-        compliance: Literal['soft', 'hard'] = 'soft'
+        compliance: Literal['lenient', 'strict'] = 'lenient'
 ) -> List[Union[Any, CodeSystem, type, str]]:
     """Parses a string representing of one or multiple data types or code systems to a list of `type` in Python
 
@@ -26,8 +26,8 @@ def parse_data_type(
     inclusion in the list passed as the `resources` parameter) to indicate that codes or terms from that resource are
     permittable.
 
-    When `compliance` is set to `'soft'` (default), this method only issues warnings if a data type is unrecognized and
-    adds a literal to the list of allowed data types. When `compliance` is set to `'hard'`, it throws a `ValueError` in
+    When `compliance` is set to `'lenient'` (default), this method only issues warnings if a data type is unrecognized and
+    adds a literal to the list of allowed data types. When `compliance` is set to `'strict'`, it throws a `ValueError` in
     the case described above.
 
     E.g.
@@ -56,7 +56,7 @@ def parse_data_type(
 def parse_single_data_type(
         type_str: str,
         resources: List[CodeSystem],
-        compliance: Literal['soft', 'hard'] = 'soft'
+        compliance: Literal['lenient', 'strict'] = 'lenient'
 ) -> Union[Any, CodeSystem, type, str]:
     """Parses a string representing a data type to the `type` in Python
 
@@ -82,7 +82,7 @@ def parse_single_data_type(
                 return type_
 
     # if nothing has matched
-    if compliance == 'soft':
+    if compliance == 'lenient':
         print(f"Warning: The type {type_str} could not be parsed to a type or resource. If it refers to a resource,"
               f" please add it to the list of resources. Otherwise, check your file.")
         return type_str

src/phenopacket_mapper/utils/parsing/parse_date.py

@@ -9,7 +9,7 @@
 def parse_date(
         date_str: str,
         default_first: Literal["day", "month"] = "day",
-        compliance: Literal['soft', 'hard'] = 'soft',
+        compliance: Literal['lenient', 'strict'] = 'lenient',
 ) -> Optional[Date]:
     """Parse a date string into a Date object
 
@@ -90,7 +90,7 @@ def parse_date(
                 return Date(year=parse_int(units[2]), month=month, day=day)
 
     else:
-        if compliance == 'hard':
+        if compliance == 'strict':
             raise ValueError(f"Invalid date string '{date_str}': no separators found")
         else:
             warnings.warn(f"Invalid date string '{date_str}': could not be parsed, returning None")
@@ -102,10 +102,10 @@ def _wrapper__most_likely_date_and_month(
         str1: str,
         full_date_str: str,
         default_first: Literal["day", "month"] = "day",
-        compliance: Literal['soft', 'hard'] = 'soft'
+        compliance: Literal['lenient', 'strict'] = 'lenient'
 ) -> Tuple[int, int]:
     """
-    Wrapper for _return_most_likely_date_and_month that raises an error if the compliance is set to 'hard'
+    Wrapper for _return_most_likely_date_and_month that raises an error if the compliance is set to 'strict'
 
     returns the day and month from the most likely date and month from two strings
 
@@ -117,7 +117,7 @@ def _wrapper__most_likely_date_and_month(
     :return: the day and month from the most likely date and month from two strings
     """
     result = _return_most_likely_date_and_month(str0, str1, full_date_str, default_first)
-    if result['inference'] and compliance == 'hard':
+    if result['inference'] and compliance == 'strict':
         raise ValueError(f"Invalid date string '{full_date_str}': unclear which unit of time is first")
     day = result['day']
     month = result['month']

src/phenopacket_mapper/utils/parsing/parse_value.py

@@ -7,7 +7,7 @@
 def parse_value(
         value_str: str,
         resources: List[CodeSystem],
-        compliance: Literal['hard', 'soft'] = 'soft'
+        compliance: Literal['strict', 'lenient'] = 'lenient'
 ) -> Union[Coding, CodeableConcept, CodeSystem, str, bool, int, float, Date, type]:
     """Parses a string representing a value to the appropriate type
     
@@ -27,15 +27,15 @@ def parse_value(
 
     # parsing as a date
     try:
-        value = parse_date(date_str=value_str, compliance='hard')
+        value = parse_date(date_str=value_str, compliance='strict')
     except ValueError:
         pass
     else:
         return value
 
     # parsing as a coding
     try:
-        value = parse_coding(coding_str=value_str, resources=resources, compliance='hard')
+        value = parse_coding(coding_str=value_str, resources=resources, compliance='strict')
     except ValueError:
         pass
     else:
@@ -50,7 +50,7 @@ def parse_value(
     else:
         return value
 
-    if compliance == 'hard':
+    if compliance == 'strict':
         raise ValueError(f"Could not parse value: {value_str}")
     else:
         print(f"Warning: Could not parse value: {value_str}")

src/phenopacket_mapper/utils/parsing/parse_value_set.py

@@ -10,7 +10,7 @@ def parse_value_set(
         value_set_name: str = "",
         value_set_description: str = "",
         resources: List[CodeSystem] = None,
-        compliance: Literal['hard', 'soft'] = 'soft',
+        compliance: Literal['strict', 'lenient'] = 'lenient',
 ) -> ValueSet:
     """Parses a value set from a string representation
 
@@ -25,7 +25,7 @@ def parse_value_set(
     :return: A ValueSet object as defined by the string representation
     """
     if not isinstance(value_set_str, str) or not value_set_str:
-        if compliance == 'hard':
+        if compliance == 'strict':
             raise ValueError(f"value_set_str must be a string, not {type(value_set_str)} ({value_set_str})")
         else:
             return ValueSet(elements=[Any], description=value_set_description)
@@ -43,15 +43,15 @@ def parse_value_set(
 
         # parsing as a data type
         try:
-            # compliance is set to 'hard' because we want to raise an error if the element is not recognized
-            element = parse_single_data_type(type_str=element_str, resources=resources, compliance='hard')
+            # compliance is set to 'strict' because we want to raise an error if the element is not recognized
+            element = parse_single_data_type(type_str=element_str, resources=resources, compliance='strict')
         except ValueError:  # parsing as type failed, parsing as a value
             element = parse_value(value_str=element_str, resources=resources)
 
         if element is not None:
             elements.append(element)
         else:
-            if compliance == 'hard':
+            if compliance == 'strict':
                 raise ValueError(f"Could not parse element: {element_str}")
             else:
                 elements.append(element_str)