def load_predefined_recognizers(self):
# TODO: Change the code to dynamic loading -
# Task #598: Support loading of the pre-defined recognizers
# from the given path.
# Currently this is not integrated into the init method to speed up
# loading time if these are not actually needed (SpaCy for example) is
# time consuming to load
self.recognizers.extend([
CreditCardRecognizer(),
DomainRecognizer(),
EmailRecognizer(),
IbanRecognizer(),
IpRecognizer(),
NhsRecognizer(),
UsBankRecognizer(),
UsLicenseRecognizer(),
UsItinRecognizer(),
UsPassportRecognizer(),
UsPhoneRecognizer(),
UsSsnRecognizer()
])
# Okera addition
if 'PRESIDIO_DISABLE_ML' in os.environ and \
os.environ['PRESIDIO_DISABLE_ML'] == 'true':
logging.info("Disabling ML recognizer.")
else:
logging.info("Enabling ML recognizer.")
self.recognizers.extend([SpacyRecognizer()])
def load_recognizers(self, path):
# TODO: Change the code to dynamic loading -
# Task #598: Support loading of the pre-defined recognizers
# from the given path.
self.recognizers.extend(
[CreditCardRecognizer(),
UsPhoneRecognizer(),
DomainRecognizer()])
def load_predefined_recognizers(self):
# TODO: Change the code to dynamic loading -
# Task #598: Support loading of the pre-defined recognizers
# from the given path.
# Currently this is not integrated into the init method to speed up
# loading time if these are not actually needed (SpaCy for example) is
# time consuming to load
self.recognizers.extend([
CreditCardRecognizer(),
CryptoRecognizer(),
DomainRecognizer(),
EmailRecognizer(),
IbanRecognizer(),
IpRecognizer(),
NhsRecognizer(),
UsBankRecognizer(),
UsLicenseRecognizer(),
UsItinRecognizer(),
UsPassportRecognizer(),
UsPhoneRecognizer(),
UsSsnRecognizer(),
SpacyRecognizer()
])
from unittest import TestCase
import os
import pytest
from analyzer import PatternRecognizer, Pattern
from analyzer.predefined_recognizers import CreditCardRecognizer, \
UsPhoneRecognizer, DomainRecognizer, UsItinRecognizer, \
UsLicenseRecognizer, UsBankRecognizer, UsPassportRecognizer, \
IpRecognizer, UsSsnRecognizer
from analyzer.nlp_engine import SpacyNlpEngine, NlpArtifacts
ip_recognizer = IpRecognizer()
us_ssn_recognizer = UsSsnRecognizer()
phone_recognizer = UsPhoneRecognizer()
us_itin_recognizer = UsItinRecognizer()
us_license_recognizer = UsLicenseRecognizer()
us_bank_recognizer = UsBankRecognizer()
us_passport_recognizer = UsPassportRecognizer()
@pytest.fixture(scope="class")
def sentences_with_context(request):
""" Loads up a group of sentences with relevant context words
"""
path = os.path.dirname(__file__) + '/data/context_sentences_tests.txt'
f = open(path, "r")
if not f.mode == 'r':
return []
content = f.read()