def __init__(self):
patterns = [
Pattern('Nric (weak) ', WEAK_REGEX, 0.3),
Pattern('Nric (medium) ', MEDIUM_REGEX, 0.5),
]
super().__init__(supported_entity="SG_NRIC_FIN",
patterns=patterns,
context=CONTEXT)
def __init__(self):
patterns = [Pattern('Driver License - WA (weak) ', WA_WEAK_REGEX, 0.4),
Pattern('Driver License - Alphanumeric (weak) ',
ALPHANUMERIC_REGEX, 0.3),
Pattern('Driver License - Digits (very weak)',
DIGITS_REGEX, 0.01)]
super().__init__(supported_entity="US_DRIVER_LICENSE",
patterns=patterns, context=LICENSE_CONTEXT)
def __init__(self):
patterns = [
Pattern('IPv4', IP_V4_REGEX, 0.6),
Pattern('IPv6', IP_V6_REGEX, 0.6)
]
super().__init__(supported_entity="IP_ADDRESS",
patterns=patterns,
context=IP_CONTEXT)
def __init__(self):
patterns = [
Pattern('SSN (very weak)', VERY_WEAK_REGEX, 0.05),
Pattern('SSN (weak)', WEAK_REGEX, 0.3),
Pattern('SSN (medium)', MEDIUM_REGEX, 0.5)
]
super().__init__(supported_entity="US_SSN",
patterns=patterns,
context=CONTEXT)
def test_no_entity_for_pattern_recognizer(self):
with pytest.raises(ValueError):
patterns = [
Pattern("p1", "someregex", 1.0),
Pattern("p1", "someregex", 0.5)
]
MockRecognizer(entity=[],
patterns=patterns,
black_list=[],
name=None,
context=None)
def __init__(self):
patterns = [
Pattern('Phone (strong)', UsPhoneRecognizer.STRONG_REGEX,
UsPhoneRecognizer.STRONG_REGEX_SCORE),
Pattern('Phone (medium)', UsPhoneRecognizer.MEDIUM_REGEX,
UsPhoneRecognizer.MEDIUM_REGEX_SCORE),
Pattern('Phone (weak)', UsPhoneRecognizer.WEAK_REGEX,
UsPhoneRecognizer.WEAK_REGEX_SCORE)
]
super().__init__(supported_entity="PHONE_NUMBER",
patterns=patterns,
context=CONTEXT)
def get_all_recognizers(self):
"""
Returns a list of CustomRecognizer which were created from the
recognizers stored in the underlying store
"""
req = recognizers_store_pb2.RecognizersGetAllRequest()
raw_recognizers = []
try:
raw_recognizers = self.rs_stub.ApplyGetAll(req).recognizers
except grpc.RpcError:
logging.info("Failed getting recognizers from the remote store. \
Returning an empty list")
return raw_recognizers
custom_recognizers = []
for new_recognizer in raw_recognizers:
patterns = []
for pat in new_recognizer.patterns:
patterns.extend([Pattern(pat.name, pat.regex, pat.score)])
new_custom_recognizer = PatternRecognizer(
name=new_recognizer.name,
supported_entity=new_recognizer.entity,
supported_language=new_recognizer.language,
black_list=new_recognizer.blacklist,
context=new_recognizer.contextPhrases,
patterns=patterns)
custom_recognizers.append(new_custom_recognizer)
return custom_recognizers
def from_dict(cls, entity_recognizer_dict):
patterns = entity_recognizer_dict.get("patterns")
if patterns:
patterns_list = [Pattern.from_dict(pat) for pat in patterns]
entity_recognizer_dict['patterns'] = patterns_list
return cls(**entity_recognizer_dict)
def test_added_pattern_recognizer_works(self):
pattern = Pattern("rocket pattern", r'\W*(rocket)\W*', 0.8)
pattern_recognizer = PatternRecognizer("ROCKET",
name="Rocket recognizer",
patterns=[pattern])
# Make sure the analyzer doesn't get this entity
recognizers_store_api_mock = RecognizerStoreApiMock()
analyze_engine = AnalyzerEngine(
registry=MockRecognizerRegistry(recognizers_store_api_mock),
nlp_engine=MockNlpEngine())
text = "rocket is my favorite transportation"
entities = ["CREDIT_CARD", "ROCKET"]
results = analyze_engine.analyze(self.unit_test_guid,
text=text,
entities=entities,
language='en',
all_fields=False)
assert len(results) == 0
# Add a new recognizer for the word "rocket" (case insensitive)
recognizers_store_api_mock.add_custom_pattern_recognizer(
pattern_recognizer)
# Check that the entity is recognized:
results = analyze_engine.analyze(self.unit_test_guid,
text=text,
entities=entities,
language='en',
all_fields=False)
assert len(results) == 1
assert_result(results[0], "ROCKET", 0, 7, 0.8)
def test_remove_pattern_recognizer(self):
pattern = Pattern("spaceship pattern", r'\W*(spaceship)\W*', 0.8)
pattern_recognizer = PatternRecognizer("SPACESHIP",
name="Spaceship recognizer",
patterns=[pattern])
# Make sure the analyzer doesn't get this entity
recognizers_store_api_mock = RecognizerStoreApiMock()
recognizer_registry = RecognizerRegistry(recognizers_store_api_mock)
# Expects zero custom recognizers
recognizers = recognizer_registry.get_custom_recognizers()
assert len(recognizers) == 0
# Add a new recognizer for the word "rocket" (case insensitive)
recognizers_store_api_mock.add_custom_pattern_recognizer(
pattern_recognizer)
# Expects one custom recognizer
recognizers = recognizer_registry.get_custom_recognizers()
assert len(recognizers) == 1
# Remove recognizer
recognizers_store_api_mock.remove_recognizer("Spaceship recognizer")
# Expects zero custom recognizers
recognizers = recognizer_registry.get_custom_recognizers()
assert len(recognizers) == 0
def __init__(self):
patterns = [
Pattern('IBAN Generic', IBAN_GENERIC_REGEX, IBAN_GENERIC_SCORE)
]
super().__init__(supported_entity="IBAN_CODE",
patterns=patterns,
context=CONTEXT)
def test_from_dict(self):
expected = my_pattern
actual = Pattern.from_dict(my_pattern_dict)
assert expected.name == actual.name
assert expected.score == actual.score
assert expected.regex == actual.regex
def test_context_custom_recognizer(self):
nlp_engine = SpacyNlpEngine()
mock_nlp_artifacts = NlpArtifacts([], [], [], [], None, "en")
# This test checks that a custom recognizer is also enhanced by context.
# However this test also verifies a specific case in which the pattern also
# includes a preceeding space (' rocket'). This in turn cause for a misalignment
# between the tokens and the regex match (the token will be just 'rocket').
# This misalignment is handled in order to find the correct context window.
rocket_recognizer = PatternRecognizer(
supported_entity="ROCKET",
name="rocketrecognizer",
context=["cool"],
patterns=[Pattern("rocketpattern", "\\s+(rocket)", 0.3)])
text = "hi, this is a cool ROCKET"
recognizer = rocket_recognizer
entities = ["ROCKET"]
nlp_artifacts = nlp_engine.process_text(text, "en")
results_without_context = recognizer.analyze(text, entities,
mock_nlp_artifacts)
results_with_context = recognizer.analyze(text, entities,
nlp_artifacts)
assert (len(results_without_context) == len(results_with_context))
for i in range(len(results_with_context)):
assert (results_without_context[i].score <
results_with_context[i].score)
def __black_list_to_regex(black_list):
"""
Converts a list of word to a matching regex, to be analyzed by the
regex engine as a part of the analyze logic
:param black_list: the list of words to detect
:return:the regex of the words for detection
"""
regex = r"(?:^|(?<= ))(" + '|'.join(black_list) + r")(?:(?= )|$)"
return Pattern(name="black_list", regex=regex, score=1.0)
def test_removed_pattern_recognizer_doesnt_work(self):
pattern = Pattern("spaceship pattern", r'\W*(spaceship)\W*', 0.8)
pattern_recognizer = PatternRecognizer("SPACESHIP",
name="Spaceship recognizer",
patterns=[pattern])
# Make sure the analyzer doesn't get this entity
recognizers_store_api_mock = RecognizerStoreApiMock()
analyze_engine = AnalyzerEngine(
registry=MockRecognizerRegistry(recognizers_store_api_mock),
nlp_engine=MockNlpEngine())
text = "spaceship is my favorite transportation"
entities = ["CREDIT_CARD", "SPACESHIP"]
results = analyze_engine.analyze(self.unit_test_guid,
text=text,
entities=entities,
language='en',
all_fields=False)
assert len(results) == 0
# Add a new recognizer for the word "rocket" (case insensitive)
recognizers_store_api_mock.add_custom_pattern_recognizer(
pattern_recognizer)
# Check that the entity is recognized:
results = analyze_engine.analyze(self.unit_test_guid,
text=text,
entities=entities,
language='en',
all_fields=False)
assert len(results) == 1
assert_result(results[0], "SPACESHIP", 0, 10, 0.8)
# Remove recognizer
recognizers_store_api_mock.remove_recognizer("Spaceship recognizer")
# Test again to see we didn't get any results
results = analyze_engine.analyze(self.unit_test_guid,
text=text,
entities=entities,
language='en',
all_fields=False)
assert len(results) == 0
def add_custom_pattern_recognizer(self, new_recognizer,
skip_hash_update=False):
patterns = []
for pat in new_recognizer.patterns:
patterns.extend([Pattern(pat.name, pat.regex, pat.score)])
new_custom_recognizer = PatternRecognizer(name=new_recognizer.name, supported_entity=new_recognizer.supported_entities[0],
supported_language=new_recognizer.supported_language,
black_list=new_recognizer.black_list,
context=new_recognizer.context,
patterns=patterns)
self.recognizers.append(new_custom_recognizer)
if skip_hash_update:
return
m = hashlib.md5()
for recognizer in self.recognizers:
m.update(recognizer.name.encode('utf-8'))
self.latest_hash = m.digest()
def test_add_pattern_recognizer(self):
pattern = Pattern("rocket pattern", r'\W*(rocket)\W*', 0.8)
pattern_recognizer = PatternRecognizer("ROCKET",
name="Rocket recognizer",
patterns=[pattern])
# Make sure the analyzer doesn't get this entity
recognizers_store_api_mock = RecognizerStoreApiMock()
recognizer_registry = RecognizerRegistry(recognizers_store_api_mock)
recognizers = recognizer_registry.get_custom_recognizers()
assert len(recognizers) == 0
# Add a new recognizer for the word "rocket" (case insensitive)
recognizers_store_api_mock.add_custom_pattern_recognizer(
pattern_recognizer)
recognizers = recognizer_registry.get_custom_recognizers()
assert len(recognizers) == 1
assert recognizers[0].patterns[0].name == "rocket pattern"
assert recognizers[0].name == "Rocket recognizer"
def test_cache_logic(self):
pattern = Pattern("rocket pattern", r'\W*(rocket)\W*', 0.8)
pattern_recognizer = PatternRecognizer("ROCKET",
name="Rocket recognizer",
patterns=[pattern])
# Negative flow
recognizers_store_api_mock = RecognizerStoreApiMock()
recognizer_registry = RecognizerRegistry(recognizers_store_api_mock)
custom_recognizers = recognizer_registry.get_custom_recognizers()
# Nothing should be returned
assert len(custom_recognizers) == 0
# Since no hash was returned, then no access to storage is expected
assert recognizers_store_api_mock.times_accessed_storage == 0
# Add a new recognizer
recognizers_store_api_mock.add_custom_pattern_recognizer(
pattern_recognizer,
skip_hash_update=True)
# Since the hash wasn't updated the recognizers are stale from the cache
# without the newly added one
custom_recognizers = recognizer_registry.get_custom_recognizers()
assert len(custom_recognizers) == 0
# And we also didn't accessed the underlying storage
assert recognizers_store_api_mock.times_accessed_storage == 0
# Positive flow
# Now do the same only this time update the hash so it should work properly
recognizers_store_api_mock = RecognizerStoreApiMock()
recognizer_registry = RecognizerRegistry(recognizers_store_api_mock)
recognizer_registry.get_custom_recognizers()
assert recognizers_store_api_mock.times_accessed_storage == 0
recognizers_store_api_mock.add_custom_pattern_recognizer(
pattern_recognizer,
skip_hash_update=False)
custom_recognizers = recognizer_registry.get_custom_recognizers()
assert len(custom_recognizers) == 1
# Accessed again
assert recognizers_store_api_mock.times_accessed_storage == 1
def __init__(self):
patterns = [Pattern('Passport (very weak)', VERY_WEAK_REGEX, 0.2)]
super().__init__(supported_entity="US_PASSPORT",
patterns=patterns,
context=CONTEXT)
def get_mock_pattern_recognizer(self, lang, entity, name):
return PatternRecognizer(
supported_entity=entity,
supported_language=lang,
name=name,
patterns=[Pattern("pat", regex="REGEX", score=1.0)])
def __init__(self):
patterns = [Pattern('Email (Medium)', REGEX, 0.5)]
super().__init__(supported_entity="EMAIL_ADDRESS",
patterns=patterns,
context=CONTEXT)
def __init__(self):
patterns = [Pattern('Crypto (Medium)', REGEX, 0.5)]
super().__init__(supported_entity="CRYPTO", patterns=patterns,
context=CONTEXT)
def __init__(self):
patterns = [Pattern('All Credit Cards (weak)', REGEX, 0.2)]
super().__init__(supported_entity="CREDIT_CARD",
patterns=patterns,
context=CONTEXT)
def __init__(self):
patterns = [Pattern('Domain ()', REGEX, 0.5)]
super().__init__(supported_entity="DOMAIN_NAME",
patterns=patterns,
context=CONTEXT)
def __init__(self):
patterns = [Pattern('NHS (medium)', REGEX, 0.5)]
super().__init__(supported_entity="UK_NHS",
patterns=patterns,
context=CONTEXT)
from unittest import TestCase
from analyzer import Pattern
my_pattern = Pattern(name="my pattern", score=0.9, regex="[re]")
my_pattern_dict = {"name": "my pattern", "regex": "[re]", "score": 0.9}
class TestPattern(TestCase):
def test_to_dict(self):
expected = my_pattern_dict
actual = my_pattern.to_dict()
assert expected == actual
def test_from_dict(self):
expected = my_pattern
actual = Pattern.from_dict(my_pattern_dict)
assert expected.name == actual.name
assert expected.score == actual.score
assert expected.regex == actual.regex
def __init__(self):
patterns = [Pattern('Bank Account (weak)', REGEX, 0.05)]
super().__init__(supported_entity="US_BANK_NUMBER",
patterns=patterns,
context=CONTEXT)
