def parse(self, log: ProcessLogger, text, text_unit_id, text_unit_lang, **kwargs) -> ParseResults:
court_config = dict_data_cache.get_court_config()
found = [dict_entities.get_entity_id(i[0])
for i in courts.get_courts(text,
court_config_list=court_config,
text_languages=[text_unit_lang])]
if found:
unique = set(found)
return ParseResults({CourtUsage: [CourtUsage(text_unit_id=text_unit_id,
court_id=court_id,
count=found.count(court_id)) for court_id in unique]})
def parse(self, log: ProcessLogger, text, text_unit_id, text_unit_lang,
document_initial_load: bool = False, **kwargs) -> ParseResults:
from apps.extract.app_vars import SIMPLE_LOCATOR_TOKENIZATION
simple_norm = SIMPLE_LOCATOR_TOKENIZATION.val
court_config = dict_data_cache.get_court_config()
found = [i[0].id
for i in courts.get_courts(text,
court_config_list=court_config,
text_languages=[text_unit_lang],
simplified_normalization=simple_norm)]
if found:
unique = set(found)
return ParseResults({CourtUsage: [CourtUsage(text_unit_id=text_unit_id,
court_id=court_id,
count=found.count(court_id)) for court_id in unique]})