def parse(self, in_file, out_file):
output_file = open(out_file, 'w')
with open(in_file, 'r') as file:
line = file.readline()
i = 0
for line in file.readlines():
sentence = ""
line = line.strip().split('\t')
for word, flag in pseg.cut(line[1].strip()):
if flag == 'x':
continue
else:
sentence = sentence + word + " "
output_file.write(sentence.strip() + "\n")
i += 1
if i % 100 == 0:
print('Handle lines %d' % i)
评论列表
文章目录