Add a validation layer for YAML based configuration

presidio-analyzer/presidio_analyzer/analyzer_engine_provider.py

@@ -5,6 +5,7 @@
 import yaml
 
 from presidio_analyzer import AnalyzerEngine, RecognizerRegistry
+from presidio_analyzer.input_validation import ConfigurationValidator
 from presidio_analyzer.nlp_engine import NlpEngine, NlpEngineProvider
 from presidio_analyzer.recognizer_registry import RecognizerRegistryProvider
 
@@ -29,14 +30,21 @@ def __init__(
         nlp_engine_conf_file: Optional[Union[Path, str]] = None,
         recognizer_registry_conf_file: Optional[Union[Path, str]] = None,
     ):
+        if analyzer_engine_conf_file:
+            ConfigurationValidator.validate_file_path(analyzer_engine_conf_file)
+        if nlp_engine_conf_file:
+            ConfigurationValidator.validate_file_path(nlp_engine_conf_file)
+        if recognizer_registry_conf_file:
+            ConfigurationValidator.validate_file_path(recognizer_registry_conf_file)
+
         self.configuration = self.get_configuration(conf_file=analyzer_engine_conf_file)
         self.nlp_engine_conf_file = nlp_engine_conf_file
         self.recognizer_registry_conf_file = recognizer_registry_conf_file
 
     def get_configuration(
         self, conf_file: Optional[Union[Path, str]]
     ) -> Union[Dict[str, Any]]:
-        """Retrieve the analyzer engine configuration from the provided file."""
+        """Retrieve analyzer engine configuration from the provided file."""
 
         if not conf_file:
             default_conf_file = self._get_full_conf_path()
@@ -59,10 +67,18 @@ def get_configuration(
                 with open(self._get_full_conf_path()) as file:
                     configuration = yaml.safe_load(file)
             except Exception:
-                print(f"Failed to parse file {conf_file}, resorting to default")
+                logger.warning(
+                    f"Failed to parse file {conf_file}, resorting to default"
+                )
                 with open(self._get_full_conf_path()) as file:
                     configuration = yaml.safe_load(file)
 
+        # Validate configuration using Pydantic-based ConfigurationValidator
+        from presidio_analyzer.input_validation import ConfigurationValidator
+
+        ConfigurationValidator.validate_analyzer_configuration(configuration)
+        logger.debug("Analyzer configuration validation passed")
+
         return configuration
 
     def create_engine(self) -> AnalyzerEngine:

presidio-analyzer/presidio_analyzer/analyzer_request.py

@@ -37,5 +37,6 @@ def __init__(self, req_data: Dict):
         self.context = req_data.get("context")
         self.allow_list = req_data.get("allow_list")
         self.allow_list_match = req_data.get("allow_list_match", "exact")
-        self.regex_flags = req_data.get("regex_flags",
-                                        re.DOTALL | re.MULTILINE | re.IGNORECASE)
+        self.regex_flags = req_data.get(
+            "regex_flags", re.DOTALL | re.MULTILINE | re.IGNORECASE
+        )

presidio-analyzer/presidio_analyzer/conf/default_analyzer_full.yaml

@@ -0,0 +1,154 @@
+supported_languages: 
+  - en
+default_score_threshold: 0
+nlp_configuration:
+  nlp_engine_name: spacy
+  models:
+    - lang_code: en
+      model_name: en_core_web_lg
+
+  ner_model_configuration:
+    model_to_presidio_entity_mapping:
+      PER: PERSON
+      PERSON: PERSON
+      NORP: NRP
+      FAC: LOCATION
+      LOC: LOCATION
+      LOCATION: LOCATION
+      GPE: LOCATION
+      ORG: ORGANIZATION
+      ORGANIZATION: ORGANIZATION
+      DATE: DATE_TIME
+      TIME: DATE_TIME
+
+    low_confidence_score_multiplier: 0.4
+    low_score_entity_names:
+      -
+    labels_to_ignore:
+      - ORG
+      - ORGANIZATION # has many false positives
+      - CARDINAL
+      - EVENT
+      - LANGUAGE
+      - LAW
+      - MONEY
+      - ORDINAL
+      - PERCENT
+      - PRODUCT
+      - QUANTITY
+      - WORK_OF_ART
+
+
+recognizer_registry:
+  # global_regex_flags: 26
+  recognizers:
+    # Recognizers listed here can either be loaded from the recognizers defined in code (type: predefined),
+    # or created based on the provided configuration (type: custom).
+    # For predefined:
+    # - If only a recognizer name is provided, a predefined recognizer with this name and default parameters will be loaded.
+    # - If a parameter isn't provided, the default one would be loaded.
+    # For custom:
+    # - See an example configuration here: https://github.com/microsoft/presidio/blob/main/presidio-analyzer/presidio_analyzer/conf/example_recognizers.yaml
+    # - Custom pattern recognizers with this configuration can be added to this file, with type: custom
+    #  For recognizers supporting more than one language, an instance of the recognizer for each language will be created.
+    # For example, see the CreditCardRecognizer definition below:
+    - name: CreditCardRecognizer
+      supported_languages:
+      - language: en
+        context: [credit, card, visa, mastercard, cc, amex, discover, jcb, diners, maestro, instapayment]
+      type: predefined
+
+    - name: UsBankRecognizer
+      type: predefined
+
+    - name: UsLicenseRecognizer
+      type: predefined
+
+    - name: UsItinRecognizer
+      type: predefined
+
+    - name: UsPassportRecognizer
+      type: predefined
+
+    - name: UsSsnRecognizer
+      type: predefined
+
+    - name: NhsRecognizer
+      type: predefined
+
+    - name: UkNinoRecognizer
+      type: predefined
+      enabled: false
+
+    - name: SgFinRecognizer
+      type: predefined
+      enabled: false
+
+    - name: AuAbnRecognizer
+      type: predefined
+      enabled: false
+
+    - name: AuAcnRecognizer
+      type: predefined
+      enabled: false
+
+    - name: AuTfnRecognizer
+      type: predefined
+      enabled: false
+
+    - name: AuMedicareRecognizer
+      type: predefined
+      enabled: false
+
+    - name: InPanRecognizer
+      type: predefined
+      enabled: false
+
+    - name: InAadhaarRecognizer
+      supported_languages:
+      - en
+      type: predefined
+      enabled: false
+
+    - name: InVehicleRegistrationRecognizer
+      type: predefined
+      enabled: false
+
+    - name: InPassportRecognizer
+      type: predefined
+      enabled: false
+
+    - name: CryptoRecognizer
+      type: predefined
+
+    - name: DateRecognizer
+      type: predefined
+
+    - name: EmailRecognizer
+      type: predefined
+
+    - name: IbanRecognizer
+      type: predefined
+
+    - name: IpRecognizer
+      type: predefined
+
+    - name: MedicalLicenseRecognizer
+      type: predefined
+
+    - name: PhoneRecognizer
+      type: predefined
+
+    - name: UrlRecognizer
+      type: predefined
+
+    - name: InVoterRecognizer
+      type: predefined
+      enabled: false
+
+    - name: InGstinRecognizer
+      type: predefined
+      enabled: false
+
+    - name: SpacyRecognizer
+      type: predefined

presidio-analyzer/presidio_analyzer/context_aware_enhancers/__init__.py

@@ -1,4 +1,5 @@
 """Context awareness modules."""
+
 from .context_aware_enhancer import ContextAwareEnhancer
 from .lemma_context_aware_enhancer import LemmaContextAwareEnhancer
 

presidio-analyzer/presidio_analyzer/input_validation/__init__.py

@@ -0,0 +1,19 @@
+"""Configuration validation module for Presidio."""
+
+from .schemas import ConfigurationValidator
+from .yaml_recognizer_models import (
+    BaseRecognizerConfig,
+    CustomRecognizerConfig,
+    LanguageContextConfig,
+    PredefinedRecognizerConfig,
+    RecognizerRegistryConfig,
+)
+
+__all__ = [
+    "ConfigurationValidator",
+    "BaseRecognizerConfig",
+    "CustomRecognizerConfig",
+    "LanguageContextConfig",
+    "PredefinedRecognizerConfig",
+    "RecognizerRegistryConfig",
+]