import re
from lexnlp.extract.en.utils import NPExtractor
act_grammar = r"""
NBAR:
{<NNP.*|JJ|\(|\)|,>*<NNP.*>} # Nouns, Adj-s, brackets, terminated with Nouns
IN:
{<CC|IN|,>} # &, and, of
NP:
{(<NBAR><IN>)*<NBAR>(<IN><CD>)?}
"""
ACT_NPE = NPExtractor(act_grammar)
ACT_NPE.exception_sym += ['And', 'Of']
ACT_RE = re.compile('\s+Act(?:\W|$)')
def get_acts(text):
act_names = [i for i in set(ACT_NPE.get_np(text)) if ACT_RE.search(i)]
for act_name in act_names:
act_name_re = re.compile(re.escape(act_name))
for match in act_name_re.finditer(text):
location_start, location_end = match.span()
yield {'location_start': location_start,
'location_end': location_end,
'value': act_name}
def get_act_list(*args, **kwargs):
return list(get_acts(*args, **kwargs))
__version__ = "0.1.6"
__maintainer__ = "LexPredict, LLC"
__email__ = "*****@*****.**"
TRADEMARK_PTN = r"[A-Z0-9][^\)]+(?:[a-z]TM|[ \(]TM(?:\W|$)|™|\s*\(R\)|Ⓡ|®)"
TRADEMARK_PTN_RE = re.compile(TRADEMARK_PTN)
grammar = r"""
NBAR:
{<NNP.*|JJ|\(|,>*<NNP.*|\)>} # Nouns, Adj-s, brackets, terminated with Nouns or brackets
IN:
{<CC|IN>} # &, and, of
NP:
{(<NBAR><IN>)*<NBAR>}
"""
np_extractor = NPExtractor(grammar=grammar)
def get_trademarks(text) -> Generator:
"""
Find trademarks in text.
:param text:
:return:
"""
# Iterate through sentences
if TRADEMARK_PTN_RE.search(text):
for sentence in get_sentence_list(text):
for phrase in np_extractor.get_np(sentence):
tms = TRADEMARK_PTN_RE.findall(phrase)
for tm in tms:
yield tm
