mirror of
https://github.com/data-privacy-stack/presidio.git
synced 2026-07-23 11:20:55 -05:00
159 lines
3.7 KiB
YAML
159 lines
3.7 KiB
YAML
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/data-privacy-stack/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: PhTinRecognizer
|
|
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
|