def test_bankr_courts_wo_nltk(self):
text = 'One one Bankr. E.D.N.C. two two two.'
courts = list(
get_courts(text,
court_config_list=self.build_courts_config(),
simplified_normalization=True))
self.assertEqual(1, len(courts))
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_courts_legacy_function(self, text: str):
court_df = pandas \
.read_csv(
"https://raw.githubusercontent.com/LexPredict/lexpredict-legal-dictionary/1.0.2/en/legal/us_courts"
".csv")
# Create config objects
court_config_list = []
for _, row in court_df.iterrows():
c = entity_config(row["Court ID"], row["Court Name"], 0,
row["Alias"].split(";") if not pandas.isnull(row["Alias"]) else [])
court_config_list.append(c)
return get_courts(text, court_config_list)
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]})
def parse_courts_legacy_function(self, text: str):
court_df = pandas \
.read_csv(
"https://raw.githubusercontent.com/LexPredict/lexpredict-legal-dictionary/1.0.2/en/legal/us_courts"
".csv")
# Create config objects
court_config_list = []
for _, row in court_df.iterrows():
aliases = []
if not pandas.isnull(row['Alias']):
aliases = [
DictionaryEntryAlias(r) for r in row['Alias'].split(';')
]
c = DictionaryEntry(id=int(row['Court ID']),
name=row['Court Name'],
priority=0,
name_is_alias=True,
aliases=aliases)
court_config_list.append(c)
return get_courts(text, court_config_list)
def test_bankr_courts(self):
text = 'One one Bankr. E.D.N.C. two two two.'
courts = list(
get_courts(text, court_config_list=self.build_courts_config()))
self.assertEqual(1, len(courts))
def extract_courts(self, text=None):
if not text:
text = self.text
return list(lex_courts.get_courts(text))
def parse_courts_legacy_function(self, text: str):
court_config_list = self.load_en_courts()
return get_courts(text, court_config_list)
