From d6893459a24ccf1dec3d52a139ca1e36dc8d3469 Mon Sep 17 00:00:00 2001 From: Nacim Date: Mon, 23 Jun 2025 21:44:51 +0200 Subject: [PATCH] Update default.yaml --- conf/default.yaml | 124 +++++++++++++++++++++++++++------------------- 1 file changed, 73 insertions(+), 51 deletions(-) diff --git a/conf/default.yaml b/conf/default.yaml index 6dd0e0f..4127a2f 100644 --- a/conf/default.yaml +++ b/conf/default.yaml @@ -1,7 +1,6 @@ # ===================================================================== -# CONFIGURATION PRESIDIO COMPLÈTE - RGPD FRANÇAIS/BELGE +# CONFIGURATION PRESIDIO COMPLÈTE - RGPD FRANÇAIS/BELGE - v3 (Précision Max) # ===================================================================== -# Langues supportées par l'ensemble du moteur supported_languages: [en, fr] # 1. CONFIGURATION DU MOTEUR NLP @@ -27,10 +26,9 @@ nlp_configuration: - WORK_OF_ART confidence_thresholds: DEFAULT_CONFIDENCE: 0.65 - entities: - PERSON: 0.85 - LOCATION: 0.75 - ORGANIZATION: 0.7 + PERSON: 0.85 + LOCATION: 0.75 + ORGANIZATION: 0.7 # 2. CONFIGURATION DU REGISTRE DES DÉTECTEURS # ===================================================================== @@ -40,87 +38,101 @@ recognizer_registry: recognizers: - name: EmailRecognizer supported_language: fr - supported_entity: EMAIL_ADDRESS # CORRECTION: entity_name -> supported_entity - patterns: - - name: Email Pattern - regex: "\\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\\.[A-Z|a-z]{2,}\\b" - score: 1.0 + supported_entity: EMAIL_ADDRESS + patterns: [{name: Email Pattern, regex: "\\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\\.[A-Z|a-z]{2,}\\b", score: 1.0}] context: ["email", "courriel", "mail"] - name: PhoneRecognizer supported_language: fr - supported_entity: PHONE_NUMBER # CORRECTION: entity_name -> supported_entity - patterns: - - name: Phone Pattern (FR/BE/LUX) - regex: "\\b(?:(?:\\+|00)?(?:32|33|352)|0)\\s?[1-9](?:[\\s.-]?\\d{2}){3,4}\\b" - score: 0.8 + supported_entity: PHONE_NUMBER + patterns: [{name: Phone Pattern (FR/BE/LUX), regex: "\\b(?:(?:\\+|00)?(?:32|33|352)|0)\\s?[1-9](?:[\\s.-]?\\d{2}){3,4}\\b", score: 0.8}] context: ["téléphone", "tel", "mobile", "gsm", "contact"] - name: IbanRecognizer supported_language: fr - supported_entity: IBAN # CORRECTION: entity_name -> supported_entity - patterns: - - name: IBAN Pattern - regex: "\\b[A-Z]{2}[0-9]{2}\\s?(?:[A-Z0-9]{4}\\s?){2,7}[A-Z0-9]{1,4}\\b" - score: 0.95 + supported_entity: IBAN + patterns: [{name: IBAN Pattern, regex: "\\b[A-Z]{2}[0-9]{2}\\s?(?:[A-Z0-9]{4}\\s?){2,7}[A-Z0-9]{1,4}\\b", score: 0.95}] context: ["iban", "compte", "bancaire"] - name: CreditCardRecognizer supported_language: fr - supported_entity: CREDIT_CARD_NUMBER # CORRECTION: entity_name -> supported_entity + supported_entity: CREDIT_CARD_NUMBER patterns: - - name: Credit Card Pattern - regex: "\\b(?:4[0-9]{12}(?:[0-9]{3})?|5[1-5][0-9]{14}|6(?:011|5[0-9]{2})[0-9]{12}|3[47][0-9]{13}|3(?:0[0-5]|[68][0-9])[0-9]{11}|(?:2131|1800|35\\d{3})\\d{11})\\b" + - name: Credit Card Pattern with spaces + regex: "\\b(?:4[0-9]{3}(?:\\s?[0-9]{4}){3}|5[1-5][0-9]{2}(?:\\s?[0-9]{4}){3}|6(?:011|5[0-9]{2})(?:\\s?[0-9]{4}){3}|3[47][0-9]{2}(?:\\s?[0-9]{6})(?:\\s?[0-9]{5})|3(?:0[0-5]|[68][0-9])(?:\\s?[0-9]{4})(?:\\s?[0-9]{4})(?:\\s?[0-9]{3})|(?:2131|1800|35\\d{3})(?:\\s?\\d{4}){2}\\d{3})\\b" score: 0.9 context: ["carte bancaire", "visa", "mastercard", "amex"] - name: MoneyRecognizer supported_language: fr - supported_entity: MONEY # CORRECTION: entity_name -> supported_entity - patterns: - - name: Money Pattern EUR - regex: "(?:EUR|€)\\s*\\d{1,3}(?:[.,\\s]\\d{3})*(?:[.,]\\d{2})?|\\d{1,3}(?:[.,\\s]\\d{3})*(?:[.,]\\d{2})?\\s*(?:EUR|€)" - score: 0.85 + supported_entity: MONEY + patterns: [{name: Money Pattern EUR, regex: "(?:EUR|€)\\s*\\d{1,3}(?:[.,\\s]\\d{3})*(?:[.,]\\d{2})?|\\d{1,3}(?:[.,\\s]\\d{3})*(?:[.,]\\d{2})?\\s*(?:EUR|€)", score: 0.85}] - name: BelgianNRNRecognizer supported_language: fr - supported_entity: BE_NATIONAL_REGISTER_NUMBER # CORRECTION: entity_name -> supported_entity - patterns: - - name: NRN Pattern - regex: "\\b[0-9]{2}\\.[0-9]{2}\\.[0-9]{2}-[0-9]{3}\\.[0-9]{2}\\b" - score: 1.0 + supported_entity: BE_NATIONAL_REGISTER_NUMBER + patterns: [{name: NRN Pattern, regex: "\\b[0-9]{2}\\.[0-9]{2}\\.[0-9]{2}-[0-9]{3}\\.[0-9]{2}\\b", score: 1.0}] context: ["registre national", "nrn", "niss"] - name: BelgianEnterpriseRecognizer supported_language: fr - supported_entity: BE_ENTERPRISE_NUMBER # CORRECTION: entity_name -> supported_entity - patterns: - - name: BE Enterprise Number - regex: "\\bBE\\s?0\\d{3}[\\.\\s]?\\d{3}[\\.\\s]?\\d{3}\\b" - score: 0.95 + supported_entity: BE_ENTERPRISE_NUMBER + patterns: [{name: BE Enterprise Number, regex: "\\bBE\\s?0\\d{3}[\\.\\s]?\\d{3}[\\.\\s]?\\d{3}\\b", score: 0.95}] context: ["numéro d'entreprise", "btw", "tva", "BCE", "KBO"] - name: FrenchINSEERecognizer supported_language: fr - supported_entity: FR_SOCIAL_SECURITY_NUMBER # CORRECTION: entity_name -> supported_entity - patterns: - - name: INSEE Pattern - regex: "\\b[12][\\s]?[0-9]{2}[\\s]?(?:0[1-9]|1[0-2])[\\s]?(?:2[ABab]|[0-9]{2})[\\s]?[0-9]{3}[\\s]?[0-9]{3}[\\s]?[0-9]{2}\\b" - score: 0.95 + supported_entity: FR_SOCIAL_SECURITY_NUMBER + patterns: [{name: INSEE Pattern, regex: "\\b[12][\\s]?[0-9]{2}[\\s]?(?:0[1-9]|1[0-2])[\\s]?(?:2[ABab]|[0-9]{2})[\\s]?[0-9]{3}[\\s]?[0-9]{3}[\\s]?[0-9]{2}\\b", score: 0.95}] context: ["sécurité sociale", "insee", "nir"] - name: FrenchSIRENSIRETRecognizer supported_language: fr - supported_entity: FR_SIREN_SIRET # CORRECTION: entity_name -> supported_entity + supported_entity: FR_SIREN_SIRET patterns: - - name: SIRET Pattern - regex: "\\b[0-9]{3}[\\s]?[0-9]{3}[\\s]?[0-9]{3}[\\s]?[0-9]{5}\\b" - score: 0.9 - - name: SIREN Pattern - regex: "\\b[0-9]{3}[\\s]?[0-9]{3}[\\s]?[0-9]{3}\\b" - score: 0.85 + - {name: SIRET Pattern, regex: "\\b[0-9]{3}[\\s]?[0-9]{3}[\\s]?[0-9]{3}[\\s]?[0-9]{5}\\b", score: 0.9} + - {name: SIREN Pattern, regex: "\\b[0-9]{3}[\\s]?[0-9]{3}[\\s]?[0-9]{3}\\b", score: 0.85} context: ["siren", "siret"] + - name: BelgianIDCardRecognizer + supported_language: fr + supported_entity: BE_ID_CARD_NUMBER + patterns: [{name: "Belgian ID Card Number", regex: "\\b\\d{3}-\\d{7}-\\d{2}\\b", score: 1.0}] + context: ["carte d'identité", "eid"] + + - name: BelgianLicensePlateRecognizer + supported_language: fr + supported_entity: BE_LICENSE_PLATE + patterns: [{name: "Belgian License Plate", regex: "\\b(?:[12]-\\w{3}-\\d{3}|\\w{3}-\\d{3})\\b", score: 0.8}] + context: ["plaque", "immatriculation"] + + - name: BICRecognizer + supported_language: fr + supported_entity: BE_BIC + patterns: + - name: BIC/SWIFT Code + regex: "\\b[A-Z]{6}[A-Z0-9]{2}(?:[A-Z0-9]{3})?\\b" + score: 1.0 + context: ["bic", "swift"] + + - name: JobTitleRecognizer + supported_language: fr + supported_entity: JOB_TITLE + patterns: + - name: Common Job Titles + regex: "(?i)\\b(Gérant|Directeur|Directrice|Président|CEO|CFO|CTO|Manager|Responsable|Chef de projet)\\b" + score: 0.8 + context: ["représentée par", "fonction", "poste", "attention de"] + + - name: CompanyFormRecognizer + supported_language: fr + supported_entity: LEGAL_FORM + patterns: + - name: Common Legal Forms + regex: "\\b(SPRL|SA|SCS|SNC|SCRI|SCA|SRL|SC)\\b" + score: 0.9 + context: ["société", "entreprise"] + # 3. LISTE D'EXCLUSION # ===================================================================== allow_list: @@ -196,6 +208,11 @@ anonymizer_config: BE_ENTERPRISE_NUMBER: replace FR_SOCIAL_SECURITY_NUMBER: replace FR_SIREN_SIRET: replace + BE_ID_CARD_NUMBER: replace + BE_LICENSE_PLATE: replace + BE_BIC: replace + JOB_TITLE: replace + LEGAL_FORM: replace replacements: PERSON: "" @@ -213,3 +230,8 @@ anonymizer_config: BE_ENTERPRISE_NUMBER: "" FR_SOCIAL_SECURITY_NUMBER: "" FR_SIREN_SIRET: "" + BE_ID_CARD_NUMBER: "" + BE_LICENSE_PLATE: "" + BE_BIC: "" + JOB_TITLE: "" + LEGAL_FORM: ""