def depend_parse():
ht0 = HarvestText()
para = "上港的武磊武球王是中国最好的前锋。"
entity_mention_dict = {'武磊': ['武磊', '武球王'], "上海上港": ["上港"]}
entity_type_dict = {'武磊': '球员', "上海上港": "球队"}
ht0.add_entities(entity_mention_dict, entity_type_dict)
for arc in ht0.dependency_parse(para):
print(arc)
print(ht0.triple_extraction(para))
def test_depend_parse():
sys.stdout, expected = open(get_current_function_name()+"_current","w"), open(get_current_function_name()+"_expected").read()
ht0 = HarvestText()
para = "上港的武磊武球王是中国最好的前锋。"
entity_mention_dict = {'武磊': ['武磊', '武球王'], "上海上港":["上港"]}
entity_type_dict = {'武磊': '球员', "上海上港":"球队"}
ht0.add_entities(entity_mention_dict, entity_type_dict)
for arc in ht0.dependency_parse(para):
print(arc)
print(ht0.triple_extraction(para))
sys.stdout.close()
assert open(get_current_function_name() + "_current").read() == expected
def get_seq(text):
"""
获取关键内容
三元组抽取
"""
ht=HarvestText()
s=[]
text=tkitText.Text().clear(text)
for item in ht.triple_extraction(sent=text, standard_name=False, stopwords=None, expand = "all"):
if item=='':
pass
else:
# print(' '.join(item))
# s.append(str(item))
s.append(''.join(item))
# s="。".join(s)
return s
from harvesttext import HarvestText
ht0 = HarvestText()
s = "nnn"
print("ht知识：", ht0.triple_extraction(sent=s, expand="exclude_entity"))
