def __analyze_patterns(
self, text: str, flags: int = None
) -> List[RecognizerResult]:
"""
Evaluate all patterns in the provided text.
Including words in the provided deny-list
:param text: text to analyze
:param flags: regex flags
:return: A list of RecognizerResult
"""
flags = flags if flags else re.DOTALL | re.MULTILINE
results = []
for pattern in self.patterns:
match_start_time = datetime.datetime.now()
matches = re.finditer(pattern.regex, text, flags=flags)
match_time = datetime.datetime.now() - match_start_time
logger.debug(
"--- match_time[%s]: %s.%s seconds",
pattern.name,
match_time.seconds,
match_time.microseconds,
)
for match in matches:
start, end = match.span()
current_match = text[start:end]
# Skip empty results
if current_match == "":
continue
score = pattern.score
validation_result = self.validate_result(current_match)
description = self.build_regex_explanation(
self.name, pattern.name, pattern.regex, score, validation_result
)
pattern_result = RecognizerResult(
self.supported_entities[0], start, end, score, description
)
if validation_result is not None:
if validation_result:
pattern_result.score = EntityRecognizer.MAX_SCORE
else:
pattern_result.score = EntityRecognizer.MIN_SCORE
invalidation_result = self.invalidate_result(current_match)
if invalidation_result is not None and invalidation_result:
pattern_result.score = EntityRecognizer.MIN_SCORE
if pattern_result.score > EntityRecognizer.MIN_SCORE:
results.append(pattern_result)
results = EntityRecognizer.remove_duplicates(results)
return results
def __analyze_patterns(self, text):
"""
Evaluates all patterns in the provided text, including words in
the provided blacklist
In a sentence we could get a false positive at the end of our regex, were we
want to find the IBAN but not the false positive at the end of the match.
i.e. "I want my deposit in DE89370400440532013000 2 days from today."
:param text: text to analyze
:param flags: regex flags
:return: A list of RecognizerResult
"""
results = []
for pattern in self.patterns:
matches = re.finditer(pattern.regex, text, flags=self.flags)
for match in matches:
for grp_num in reversed(range(1, len(match.groups()) + 1)):
start = match.span(0)[0]
end = (
match.span(grp_num)[1]
if match.span(grp_num)[1] > 0
else match.span(0)[1]
)
current_match = text[start:end]
# Skip empty results
if current_match == "":
continue
score = pattern.score
validation_result = self.validate_result(current_match)
description = PatternRecognizer.build_regex_explanation(
self.name, pattern.name, pattern.regex, score, validation_result
)
pattern_result = RecognizerResult(
self.supported_entities[0], start, end, score, description
)
if validation_result is not None:
if validation_result:
pattern_result.score = EntityRecognizer.MAX_SCORE
else:
pattern_result.score = EntityRecognizer.MIN_SCORE
if pattern_result.score > EntityRecognizer.MIN_SCORE:
results.append(pattern_result)
break
return results
def __analyze_patterns(self, text):
"""
Evaluates all patterns in the provided text, including words in
the provided blacklist
:param text: text to analyze
:return: A list of RecognizerResult
"""
results = []
for pattern in self.patterns:
match_start_time = datetime.datetime.now()
matches = re.finditer(pattern.regex,
text,
flags=re.IGNORECASE | re.DOTALL
| re.MULTILINE)
match_time = datetime.datetime.now() - match_start_time
self.logger.debug('--- match_time[%s]: %s.%s seconds',
pattern.name, match_time.seconds,
match_time.microseconds)
for match in matches:
start, end = match.span()
current_match = text[start:end]
# Skip empty results
if current_match == '':
continue
score = pattern.score
validation_result = self.validate_result(current_match)
description = PatternRecognizer.build_regex_explanation(
self.name, pattern.name, pattern.regex, score,
validation_result)
pattern_result = RecognizerResult(self.supported_entities[0],
start, end, score,
description)
if validation_result is not None:
if validation_result:
pattern_result.score = EntityRecognizer.MAX_SCORE
else:
pattern_result.score = EntityRecognizer.MIN_SCORE
if pattern_result.score > EntityRecognizer.MIN_SCORE:
results.append(pattern_result)
return results
