Analysis builder improvements

presidio-structured/presidio_structured/analysis_builder.py

@@ -56,8 +56,8 @@ def generate_analysis(
     def _remove_low_scores(
         self,
         key_recognizer_result_map: Dict[str, RecognizerResult],
-        score_threshold: float = None,
-    ) -> List[RecognizerResult]:
+        score_threshold: Optional[float] = None,
+    ) -> Dict[str, RecognizerResult]:
         """
         Remove results for which the confidence is lower than the threshold.
 
@@ -127,13 +127,15 @@ def _generate_analysis_from_results_json(
         for result in analyzer_results:
             current_key = prefix + result.key
 
-            if isinstance(result.value, dict):
+            if isinstance(result.value, dict) and isinstance(
+                result.recognizer_results, Iterator
+            ):
                 nested_mappings = self._generate_analysis_from_results_json(
                     result.recognizer_results, prefix=current_key + "."
                 )
                 key_recognizer_result_map.update(nested_mappings)
             first_recognizer_result = next(iter(result.recognizer_results), None)
-            if first_recognizer_result is not None:
+            if isinstance(first_recognizer_result, RecognizerResult):
                 logger.debug(
                     f"Found result with entity {first_recognizer_result.entity_type} \
                         in {current_key}"

presidio-structured/presidio_structured/data/data_processors.py

@@ -134,7 +134,7 @@ class JsonDataProcessor(DataProcessorBase):
     """JSON Data Processor, Supports arbitrary nesting of dictionaries and lists."""
 
     @staticmethod
-    def _get_nested_value(data: Union[Dict, List], path: List[str]) -> Any:
+    def _get_nested_value(data: Union[Dict, List, None], path: List[str]) -> Any:
         """
         Recursively retrieves the value from nested data using a given path.
 

presidio-structured/presidio_structured/structured_engine.py

@@ -33,7 +33,7 @@ def anonymize(
         self,
         data: Union[Dict, DataFrame],
         structured_analysis: StructuredAnalysis,
-        operators: Dict[str, OperatorConfig] = None,
+        operators: Union[Dict[str, OperatorConfig], None] = None,
     ) -> Union[Dict, DataFrame]:
         """
         Anonymize the given data using the given configuration.
@@ -49,7 +49,7 @@ def anonymize(
         return self.data_processor.operate(data, structured_analysis, operators)
 
     def __check_or_add_default_operator(
-        self, operators: Dict[str, OperatorConfig]
+        self, operators: Union[Dict[str, OperatorConfig], None]
     ) -> Dict[str, OperatorConfig]:
         """
         Check if the provided operators dictionary has a default operator. \