This commit is contained in:
Biqoz
2025-09-15 19:04:38 +02:00
parent 3e70181b58
commit 3f9c007c9e
46 changed files with 919 additions and 146 deletions

View File

@@ -0,0 +1,20 @@
# Recognizer pour données de localisation GPS
recognizer_registry:
recognizers:
- name: LocationGPSRecognizer
supported_language: fr
supported_entity: LOCALISATION_GPS
patterns:
- name: Coordonnées GPS décimales
regex: "\\b(?:lat|latitude)\\s*[=:]?\\s*[-+]?[0-9]{1,2}\\.[0-9]{4,}\\s*,?\\s*(?:lon|lng|longitude)\\s*[=:]?\\s*[-+]?[0-9]{1,3}\\.[0-9]{4,}\\b"
score: 0.95
- name: Coordonnées simples
regex: "\\b[-+]?[0-9]{1,2}\\.[0-9]{4,}\\s*,\\s*[-+]?[0-9]{1,3}\\.[0-9]{4,}\\b"
score: 0.85
- name: Adresse MAC
regex: "\\b[0-9A-Fa-f]{2}:[0-9A-Fa-f]{2}:[0-9A-Fa-f]{2}:[0-9A-Fa-f]{2}:[0-9A-Fa-f]{2}:[0-9A-Fa-f]{2}\\b"
score: 0.9
- name: Géolocalisation
regex: "\\b(?:géolocalisation|GPS|position)\\s*:?\\s*[-+]?[0-9]{1,3}\\.[0-9]+\\s*,\\s*[-+]?[0-9]{1,3}\\.[0-9]+\\b"
score: 0.9
context: ["GPS", "coordonnées", "latitude", "longitude", "géolocalisation", "position"]

View File

@@ -0,0 +1,19 @@
# Recognizer pour URLs et identifiants en ligne
recognizer_registry:
recognizers:
- name: URLOnlineIDRecognizer
supported_language: fr
supported_entity: URL_IDENTIFIANT
patterns:
- name: URL complète
regex: "\\bhttps?://[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}(?:/[^\\s]*)?\\b"
score: 0.95
- name: Identifiant utilisateur
regex: "\\b(?:user:|username:)\\s*[a-zA-Z0-9._-]{3,20}\\b"
score: 0.85
- name: Cookie ID
regex: "\\b(?:cookie|session)\\s*[=:]\\s*[A-Za-z0-9+/=]{16,}\\b"
score: 0.9
context:
["URL", "lien", "site", "utilisateur", "connexion", "session"]