def build_regexes(self) -> None:
self.re_patient = get_regex_from_elements(self.re_patient_elements)
self.re_tp = get_regex_from_elements(self.re_tp_elements)
self.regexes_built = True
# Note that the regexes themselves may be None even if they have
# been built.
if self.debug:
log.debug("Patient scrubber: {}".format(
self.get_patient_regex_string()))
log.debug("Third party scrubber: {}".format(
self.get_tp_regex_string()))
def build_regexes(self) -> None:
"""
Compile our regexes.
"""
self.re_patient = get_regex_from_elements(self.re_patient_elements)
self.re_tp = get_regex_from_elements(self.re_tp_elements)
self.regexes_built = True
# Note that the regexes themselves may be None even if they have
# been built.
if self.debug:
log.debug(f"Patient scrubber: {self.get_patient_regex_string()}")
log.debug(f"Third party scrubber: {self.get_tp_regex_string()}")
def build(self) -> None:
"""
Compiles a high-speed scrubbing device, be it a regex or a FlashText
processor. Called only when we have collected all our words.
"""
if self.regex_method:
elements = [] # type: List[str]
for w in self.words:
elements.extend(
get_string_regex_elements(
w,
suffixes=self.suffixes,
at_word_boundaries_only=self.at_word_boundaries_only,
max_errors=self.max_errors))
log.debug(f"Building regex with {len(elements)} elements")
self._regex = get_regex_from_elements(elements)
else:
if self.words:
self._processor = KeywordProcessorFixed(case_sensitive=False)
self._processor.set_non_word_boundaries(
FLASHTEXT_WORD_CHARACTERS)
replacement = self.replacement_text
log.debug(f"Building FlashText processor with "
f"{len(self.words)} keywords")
for w in self.words:
self._processor.add_keyword(w, replacement)
else:
self._processor = None # type: Optional[KeywordProcessorFixed]
self._built = True
def build_regex(self) -> None:
elements = []
for w in self.words:
elements.extend(get_string_regex_elements(
w,
suffixes=self.suffixes,
at_word_boundaries_only=self.at_word_boundaries_only,
max_errors=self.max_errors
))
self._regex = get_regex_from_elements(elements)
self._regex_built = True
def build_regex(self) -> None:
elements = []
if self.scrub_all_uk_postcodes:
elements.extend(
get_uk_postcode_regex_elements(
at_word_boundaries_only=
self.anonymise_codes_at_word_boundaries_only))
# noinspection PyTypeChecker
for n in self.scrub_all_numbers_of_n_digits:
elements.extend(get_number_of_length_n_regex_elements(
n,
at_word_boundaries_only=(
self.anonymise_numbers_at_word_boundaries_only)
))
self._regex = get_regex_from_elements(elements)
self._regex_built = True
def build_regex(self) -> None:
"""
Compile our high-speed regex.
"""
elements = [] # type: List[str]
if self.scrub_all_uk_postcodes:
elements.extend(
get_uk_postcode_regex_elements(
at_word_boundaries_only=self.
anonymise_codes_at_word_boundaries_only))
# noinspection PyTypeChecker
for n in self.scrub_all_numbers_of_n_digits:
elements.extend(
get_number_of_length_n_regex_elements(
n,
at_word_boundaries_only=(
self.anonymise_numbers_at_word_boundaries_only)))
if self.extra_regexes:
elements.extend(self.extra_regexes)
self._regex = get_regex_from_elements(elements)
self._regex_built = True